Our news and views relating to Data Analytics, Big Data, Machine Learning, and the world of Credit.
Customers Can Predict Outcomes by Adding the Power of Psychometrics to Credit Determination
At Principa, we engage with clients and organisations across the entire credit lifecycle and track the focus of the South African credit industry. For nearly ten years the focus has consistently been in the collection space, but recently (since early 2021) this has changed and a large number of our clients are focused on acquisitions and originations.
In Part One of this two-part blog, we started providing a short overview of just some of the propensity models that Principa has developed. In this Part Two, we continue to look at different types of propensity models available across the customer engagement lifecycle that are used to predict behaviour and solve business problems.
In PART 1 of this two-part series, we explored how the current socio-economic climate resulting from the lingering financial hangover caused by the pandemic is negatively impacting the consumer's ability to settle a debt.
Although not a new concept, very few lending organisations have deployed a true multi-bureau strategy (MBS). It is however talked about fairly regularly, but often dismissed as “too hard” or “not important enough”. So why should you consider a multi-bureau strategy? What are the key considerations? How do you go about deploying a MBS? This blog hopes to address all these questions.
It has been a year and a half since the first case of the coronavirus (COVID-19) was reported from Wuhan, China. As we move into the third wave of the virus, there is an apparent dilution in both collection and recovery yields in the financial services sector, primarily because relief schemes and packages come to an end.
Propensity modelling attempts to predict the likelihood that visitors, leads and customers will perform certain actions. It’s a statistical approach that accounts for all the independent and confounding variables that affects said behaviour. The propensity score, then, is the actual probability that the visitor, lead, or customer will perform a certain action.
A scorecard is a mathematical model that is used to predict a certain outcome. In credit this might be the probability of default. The information used in a scorecard can vary, but common fields include demographic characteristics (e.g. age of applicant, number of dependants, time spent in current job) and credit bureau data (e.g. number of personal loans registered to applicant, worst arrears status on all accounts in the last 6 months).
With the large drive in account origination towards digitisation and automation, in our experience much focus has been on bedding down omni-channel capability. But the real unsung hero of an originations’ project is the API hub. In this blog I unpack API hubs and APIs available in originations.
In part 1 of this 2 part series, we looked at the available tools in working accounts optimally as well as tools available in connecting and engaging with the customer.
We all know the importance of technology within the call centre … or do we?
DecisionSmart decision engine drives innovative App that assists Saudi nationals with home ownership.
During the COVID-19 crisis, the media has focused much on the weak economy and stressed South African consumers. Figures show an increase in unemployment and for those lucky to be employed, many suffered decreased earnings through salary cuts. All this points to a highly strained economic environment.
The South African credit bureau TransUnion recently released data on the performance of various different products within the bureau in their ”Quarterly Overview of Consumer Credit Trends” for the third quarter of 2020. With the COVID-19 crisis, 2020 was characterised by a severe reduction in account originations and payment holidays in Q2 with a high increase in non-performing accounts in Q3 as payment holidays ceased and stressed consumers failed to pay their accounts.
It is common knowledge in the industry that the credit risk assessment of a consumer applying for credit is far less complex than that of a business that is applying for credit. Why is this the case? Simply put, consumers are usually very similar in their requirements and risks (homogenous) whilst businesses have far more varying risk elements (heterogenous).
Principa Decisions (Pty) L
Principa Decisions (Pty) L
Principa Decisions (Pty) L Globally there is immense pressure on collections and 2021 is due to be another year where collection departments will be forced to improve what they do and how they do it. A variety of themes have emanated over the last few months, and collection departments are focusing on how to better engage the debtors as well as the introduction of sophistication through themes such as digital collections and advanced scoring. Scoring in collections webinar In November 2020 Principa ran a “scoring in collections” webinar in partnership with CIS Kenya (equivalent of South Africa’s SACCRA). During this 1 hour and 20-minute webinar we covered a wide range of themes surrounding scoring in collections. This included how to introduce scoring into collections, the different types of scoring and then some of the bigger themes such as how machine learning might help your collections. If you’d like to know the answer to the last point, please download our free whitepaper which details how Principa have successfully deployed machine learning models and a machine learning platform at the largest debt collection agency in Africa. The list of topics covered in the webinar are the following: Collections 2020 Different types of scorecards Using a collection scorecard within a collection strategy Bringing all the models together Machine learning Contactability model considerations Settlement model considerations Q&A To watch the full webinar click here. If you’d like to discuss your collection or scoring concerns, please be in touch with us below.
Principa Decisions (Pty) Ltd.
Principa’s FinSmart has become the industry’s go-to solution set for end-to-end credit management. Our credit risk management software products reduce risk and improve profitability by streamlining processes, increasing efficiency, and automating data-driven decision making across the credit lifecycle.
Principa’s onboarding chatbot solution; Atura allows lenders to engage a customer effectively through an application process while accessing necessary data and decisioning calls using Principa’s SmartSuite software. The digital revolution “Digital” has been a financial services buzz-word for some time. Most South African lenders Principa works with have been working hard to adapt to a digital existence for several years. Some have been successful, others are still working on the challenge - and most have only partially adapted.
Principa has a wealth of experience in building and deploying chatbots for the financial services industry. Our custom-built solution is flexible and fully customisable which allows your bot to assume your brand’s persona. We can also seamlessly integrate with existing systems. Find out more.
The time is NOW for model validation and adjustment. One of the major premises used in credit scoring is that “the future is like the past”. It’s usually a rational assumption and gives us a reasonable platform on which to build scorecards whether they be application scorecards, behavioural scores, collection scores or financial models. That is reasonable until something unprecedented comes along. You can read about this black swan event in our previous two blogs here and here.
Payment holidays have been used throughout South Africa and around the world to help alleviate the economic stress during the COVID-19 lockdown. In this blog we look at some of the steps taken internationally and by some of South Africa’s major lenders (specifically in the consumer space).
If 2020 was not hit by the COVID-19 global pandemic, many were touting 2020 as the year of alternative data. In the credit assessment world, data has typically incorporated demographic data and credit bureau data (where available), but now we are seeing alternative data playing more of a role namely in cellular behavioural data and psychometrics.
Principa specialises in providing data driven solutions that will optimise your business' collections strategy, improve your recovery yields, and increase your business revenue.
Principa employs a variety of best-practice credit scorecard building techniques including mathematical programming, regression modelling, optimal segmentation-seek genetic algorithms and reject inference parceling, amongst others. Through our credit risk scorecards businesses can look to improving their credit risk decisioning by 5-30%.
Maximise profitability by reducing the churn of profitable customers Genius Retain is an analytics-as-a-service offering that allows you to statistically predict the probability of your customer cancelling their account, identify which customers are worth retaining and how to retain or re-activate these profitable customers. [FIND OUT MORE ABOUT GENIUS RETAIN] The ability to retain and re-activate dormant customers is vital to sustaining a profitable business. Companies with a clear plan to retain and activate dormant customers with a strong analytical overlay, can have a successful and profitable outcome. We discuss the value of a customer and how to retain and revive them. What is the true value of losing a customer?
In a previous blog, we looked at assessing your credit models and the challenge of building and deploying models representative of the COVID-19 crisis. At the crux of the challenge was the fact that:
“Unprecedented” is a term with which we’ve all become quite familiar over the last few months. COVID-19 has changed our society and our economy quite drastically. In predictive analytics “unprecedented” has far reaching implications – simply put it’s difficult to build models when we do not have data that reflects similar trends to what we will expect moving forward.
Effective account management strategies can prove highly profitable, particularly in a competitive marketplace where acquiring good customers is a challenge.
We are starting off with a two part blog series looking at the main requirements when considering a Collections System.
In our two previous blogs here and here we looked at how an effective account management strategy can result in profitable decisioning. In this blog we look at what is required to deploy account management strategies.
In our previous blog we introduced the value of effective account management strategies. In this blog we continue to run through different account management decision areas. In our next blog we will discuss what is needed for an effective account management strategy.
Onboarding good new customers in a very competitive market is difficult and not always that profitable. That is why prudent credit managers often look to account management strategies to reap the greater rewards. Once a customer is on-boarded and has proved herself to be an exemplary re-payer, offering her money is more of a sure-thing for repayment.Behavioural scorecards offer far better Ginis than application scorecard. This means you can afford to be more aggressive in account management.
As most of you may know by now, we are currently busy with a series of Q&A videos, so please feel free to send us your credit lifecycle related questions, or any questions relating to our products or services.
Peoples habits are changing - Are you adapting?
In our previous blog, we covered five steps to help lenders avoid application fraud. Application fraud has been an increasing blight on credit books particularly with the growth in digital channels. In this blog we explore another five fraud-mitigation steps.
After my previous video on my learnings working with self-service solutions, Peter Mackintosh sent us a question.
New technology gives the promise of greater enablement. But some of the shrewdest entrepreneurs understand that opportunity comes from the unintended consequences of new technology. So, let us take digitalisation of the loan application process: the opening of digital channels has enabled lenders to service their customers 24/7 and through APIs integrate with a host of sophisticated services. However, the advent of the digital channel has meant more opportunity for fraud. The question to ask is:
Organisations and individuals, need to adapt and change to the new ways of working to ensure that we survive this pandemic, and protect our sustainability for the future.
One of the major premises used in credit scoring is that “the future is like the past”. It’s usually a rational assumption and gives us a reasonable platform on which to build scorecards whether they be application scorecards, behavioural scores, collection scores or financial models. That is reasonable until something unprecedented comes along. You can read about this black swan event in our previous two blogs here and here
This is the second of a 2-part blog. You can read the first blog here.
One of the basic principles of credit scoring and modelling is that the “future is like the past”. Whilst robust credit models may be calibrated on multiple time periods, this assumes that trends in the past represent what is going on today. COVID-19 is a black swan event – meaning in the modern day it really is unprecedented. If you have never come across the term black swan, or if you have but no idea the origin, I recommend taking two minutes to read its really interesting etymology.
In 2011, Microsoft founder, Bill Gates, reflected on the many strides researchers have made in terms of treating diseases such as HIV, malaria and polio. Gates warned us, “There is one area, though, where the world isn’t making much progress, and that’s pandemic preparedness. This should concern us all because if history has taught us anything, it’s that there will be another deadly global pandemic”.
Principa’s Cash Vs Credit offering uses advanced analytics to help retailers answer a variety of questions. We have undergone such projects for many of South Africa’s leading retailers, and this case study describes the methodology Principa utilises to help retailers in the fashion industry.
We introduce our CollectSuite, aimed at providing organizations with a comprehensive collections execution suite.
With a recent judgment being upheld in favour of the National Credit Regulator (NCR) against Shoprite Investments Limited, we thought it would be a good time to re-look at the process of affordability assessment.
Cape Town, South Africa – 22 January 2020 - Principa, a South African data analytics company, and Digemy, a Cape Town e-learning technology provider have announced a new partnership whereby Principa will provide credit risk, and collections content and Digemy will provide their revolutionary analytics e-learning platform to manage and render the training solution.
We’ve had an excited year in credit, with a brand new partnership with UK-based Welcom Digital, to resell their award-winning account management system, Financier, in South Africa. You can read more about our partnership here.
As a data analytics company, we write about data analytics frequently: but less so on the cloud. However, as software product experts, one of our blogs on a cloud-related topic was so popular this year, we would feel terrible if you were to miss it, and so have decided to add together our data analytics and cloud topics together in this roundup.
This year, we wrote about machine learning (ML) and artificial intelligence (AI) mostly in the context of chatbots. That’s because we have a brand new relationship with NML as an Atura, AI Chatbot for Financial Services reseller. You can read more about our partnership, here. We’ve also written a very interesting blog regarding machine learning in medicine, which you shouldn’t miss, so we’ve included it in this roundup.
It’s that time of the year again: our annual roundup of top blogs! As always, we’ll be posting a series of lists of our most popular, and not-to be missed blogs grouped into our favourite topics. We’re starting with the top blogs which focus on collections and call centre topics. So without further ado, here are our top five debt collection and call centre blogs of 2019:
The current credit environment can be characterised as one of intense competition for customers, with organisations often taking additional risk to grow credit portfolios. Consumers are becoming increasingly aware of their “value” and changing their expectations of how an organisation should treat them.
Recently Principa announced their partnership with UK-based Welcom Digital. Welcom Digital’s platform Financier is one of the leading account processing platforms. Principa is now the sales and delivery partner in South Africa for Financier. We speak to Principa’s Eric Hay – a technical specialist with over 25 years’ experience with credit systems include account processing systems – who has been now appointed technical delivery head for Financier.
We recently attended the Contact Centre Management Group (CCMG) Contact Centre Conference and Expo, themed Africa's Calling.
The call centre world, unsurprisingly, ranks as one of the highest adopters of data analytics platforms year on year. This is largely due to the invaluable insights we gain through the analysis of thousands of calls received each day by the typical call centre. With speed being of the essence in making the right decision at the right time for each caller many call centres are turning to machine learning to automate their data analysis and make crucial customer experience decisions within seconds.
Recently, South Africa was faced with the threat of the biggest banking strike in our country’s history, driven by the job cuts as a result of increasing automation.
At Principa, we are passionate about new ideas and product development. 20% of our revenue is ploughed back into innovation. One of our key areas of focus is machine learning where we have built machine learning solutions in both collections and the customer acquisition space. While our focus is primarily on credit risk and customer engagement, we are always interested in how machine learning has gained traction in other industries.
Cape Town, South Africa – Welcom Digital, a UK company specialising in Loans management software, and Principa, a South African data analytics company, are delighted to announce a new strategic reseller partnership that includes the resale of Welcom Digital’s Award winning Loan Management product Financier™ to the South African market and reciprocally, Welcom Digital will market Principa’s specialised credit risk software solutions to the UK market.
Whether you’ve been involved in introducing models into your business or have had a passing interest in economic affairs, you may have come across the term “Gini-coefficient”. This blog hopes to demystify the concept and give you a good deal of information on the statistical measurement. We answer:
Collection departments utilise diallers and collections management systems to improve their collections by segmenting the delinquent customers, prioritising them and applying a host of treatments. Whilst segmentation takes you so far, there are a host of other mathematical models that can be explored to improve what we call the “Collections Cascade”. Improvement in any step of the cascade can help improve the collections yield and there are a number of models that can be used. A few of them are listed below:
What is CollectSmart? CollectSmart is a powerful, modular, enterprise-wide debt collection management system that combines business controlled segmentation with the allocation of appropriate and differentiated actions to individual customer profiles - all accessed via an easy-to-use web interface.
In today’s world, running a call centre is more difficult than ever before, with customers demanding a high level of service and a great experience at every touch point.
We talk to credit expert, Mignon Roodt, about the Debt Relief Bill, what it is and what the potential impact of the bill is.
We’re looking forward to attending this year’s Digital Customer Experience conference. The 2019 conference will be hosted by Trade Conferences International (TCI) on the 4th and 5th of September at the Indaba Hotel, Fourways, Johannesburg.
Today, more than ever before, customer service is the most important aspect of your business. With all your competitor’s that your clients can choose from, you need to offer the best experience and service to keep your customers happy – and to keep them as customers.
What is Genius Leads? Principa’s Genius Leads is a POPI compliant provision service of South African consumer leads. We use advanced analytics and Machine Learning to optimise lists of new or existing marketing leads, so you target your most desirable customers and those profiled as most likely to respond to your campaign – improving campaign take-up and long-term customer profitability.
Introducing our new generation of Principa characters, alive in a world of wonder far beyond the normal imagination, where anything is possible with data.
Staff motivation levels are an important factor in every business, but even more so in a client or prospect facing environment such as a call centre. If your call centre agents are motivated, you can expect them to remain an employee for a longer period of time, reducing staff turnover. This not only saves you a lot of resources for recruiting, but also for training.
Most websites or apps lately have a chat function, whether that be an AI-powered chatbot or a live chat function. But many people (and some businesses) don’t know the difference between the two and aren’t sure when they are talking to (or have installed) a bot or an agent.
The benefits have been recounted many times, but now that Machine Learning has the business world’s attention, how does one get started? Moving into the machine learning space can be somewhat daunting, but we hope this blog post provides some guidance that you will find helpful.
What is Atura? Atura is a powerful artificial intelligence chat solution that uses cloud technology to deliver the right answers to your customers via any device, albeit mobile, desktop or tablet. Built on the Microsoft Azure technology stack, Atura uses its advanced algorithms and machine learning techniques to correctly understand your customer request and then deliver the correct response. In the event that the AI doesn’t understand the customer request, the entire messaging conversation can be seamlessly redirected to a physical agent to further respond to your customer. The result: a fluent and seamless customer experience!
For businesses wishing to improve their credit decisions, the adoption of Mathematical Optimisation is an important consideration. Mathematical optimisation is more than a straight data-driven strategy design as it incorporates prescriptive analytics.
Deciding on which cloud service to host your core business systems on can be a daunting task. Amazon Web Services (AWS) and Microsoft Azure are two of the biggest players around, while Google Cloud and IBM Cloud are also gaining market-share.
We have released a new eBook titled Truth Seeker: a guide to avoiding logical fallacies and cognitive biases in data science.
We’re looking forward to attending this year’s Evolution of Data Science in Banking conference. The 2019 conference will be held on the 5th and 6th of June at the Indaba Hotel, Fourways, Johannesburg. The event will explore the use of data and analytical techniques to help financial services providers meet regulatory and reporting requirements. Also to be discussed is how running analytics at a product level can provide a more holistic view of customers across their portfolios.
Bringing automation into the credit assessment process through credit scoring brings about significant benefits. Some of these benefits include:
Innovative companies know they must embrace digital transformation in their business to stay competitive in the world of the fourth industrial revolution. But legacy systems often get in the way of transformation. In this blog, we look at why companies are reluctant to move away from their legacy systems and how to know when it really is time to modernise.
What is Agent X? Agent X is a call centre virtual assistant that not only guides and supports agents during calls, but motivates and inspires high performance via an engaging, dynamic and intuitive interface.
We’ve recently partnered with Atura to bring a world-class chatbot to the credit and collections industry – and we’re very excited! Your business is likely already considering a chatbot, and if not: you’ve likely got it on your agenda for this year. We’ve written recently about some powerful statistics on chatbots that you need to know, but in this article, we’ll detail some of the benefits of chatbots and why they are so important for your business in 2019.
This blog was originally published on 13 March 2019 and updated on 3 April 2019.
For a while, we have been running a blog series on cognitive biases and logical fallacies that data scientists should avoid. In this final blog on the subject, we look at some of the other logical fallacies and how they might crop up in data analytics.
According to Marketing Metrics: The Definitive Guide to Measuring Marketing Performance, the probability of selling to a new prospect is 5 to 20%, while the likelihood of selling to an existing customer is 60 to 70%. Your customer growth strategy is an easy way to grow your bottom line and improve your revenue.
If you haven’t yet heard, we’re in the chatbot game! We’ve recently announced our partnership with Atura and we’re very excited to bring the Atura chatbot into the credit and collections world.
With LinkedIn usage growing by two new members every second, you simply can’t afford to not be on the platform. Founded in 2003, LinkedIn has 590 million users with 260 million of those active every month.
The EQ Behind the IQ - Jaco Rossouw from PrincipaDecisions
Cape Town, South Africa, 20 February 2019 – Principa Decisions, a South African data analytics and software company, and Atura, a software company specialising in instant messaging technology, have announced a partnership that offers the South African credit and collections industry a solution to support originations, customer management and collections via virtual agent chatbots on mobile and desktop devices.
It is expected that IFRS9 adoption should lead to an increase in provisions (initially a balance sheet / retained earnings adjustment only with commentary on retrospective impacts). Typically, the increase is mostly a result of loss provisions for all accounts (regardless of a loss event) and the extension of the loss period from a typical 12 months to lifetime (e.g. for structured loans the remaining term of the loan plus time to default/write-off plus the recoveries window).
We’re excited to announce that we are a sponsor at this year’s 20th CET conference in South Africa! The Customer Engagement Technology Conference has been successfully bringing together marketing, digital/ IT and business heads to discover the latest solutions that enable greater customer experience in various industries.
For a while, we have been running a blog series on cognitive biases and logical fallacies that data scientists should avoid. In philosophy there are a host of informal logical fallacies – essentially errors in thinking – that crop up every day. In this series we have looked at the practice of data science to determine how these same fallacies also occur. Today we will be looking at fallacies and their manifestation in credit: The Monte-Carlo fallacy and the Hot-hand fallacy with some studies in the credit world.
Recently my team and I were sitting in a meeting with a potential client debating the basic functions of our originations software. To the business analysts who were leading the RFP process, the most critical feature seemed to be whether or not our solution would be able to offer web form fields that were customisable by the business user.
In an outbound sales environment, the agent needs to work through a long list of customers and the more information available to the agent on the customer, the better.
We apply the science of data analytics to assist our clients within various aspects of their customer-driven business and engagement process. Our products make use of predictive modelling techniques to facilitate the treatment of customers at the various stages of customer lifetime, for example during onboarding, growth and retention.
In a collections environment, an agent needs to follow up with numerous customers on their outstanding credit and the more distinct information the agent has on each customer, the better the agent will understand who they are interacting with and what the opportunities, risks and expectation of the collections call with the client are.
Common barriers to success: Skills shortage: data scientists are in high demand and in low supply. Companies lack the skills to develop advanced data analytics or machine learning applications. Cost: recruiting and building up or training a team, as well as infrastructure costs are immense. Inefficiency and low ROI on: acquisition campaigns; re-activation and retention campaigns; outbound sales calls and debt collection. Resulting in: No or ineffective use of data. High cost to get insights from data. Low returns from campaigns. What’s the alternative? Machine Learning as a Service (MLaaS): removes infrastructure skills and requirements for machine learning, allowing you to begin benefiting from machine learning quickly with little investment. Subscription based pricing, allowing you to benefit using machine learning while minimising your set-up costs and seeing returns sooner. Answers as a Service: Use historic data and machine learning to allow answers to increase in accuracy with time. MLaaS with predictive models pre-developed to answers specific questions: Genius Call Connect: What is the best time and number to call customers? Genius Customer Growth: Which customers are most likely to respond to cross-sell? Genius Re-activation: Which dormant customers are worth re-activating? Genius Customer Retention: Which customers are most likely to churn? Genius Leads: Which contacts are likely to respond to my campaign? Genius Risk Classifier: Which debtors are most likely to pay or roll? Benefits of Genius: Quick and cost-effective ability to leverage machine learning: Minimal set-up time Minimal involvement from IT Subscription based service Looking to make your data work for your business? Read more on Genius to see how it can help your business succeed.
While LinkedIn has traditionally been thought of as the business or work focussed social platform, Facebook has been making headway into gaining market share in the space as well. With company pages and groups, Facebook is catering to every interest and aspiration that people might have – and combining that with their social interactions and news sources. Facebook aims to give users a one-stop-shop experience, and it’s very good at doing it.
Our final roundup this year covers two of our main topics: customer acquisition and customer engagement. We’ve not covered these topics in depth this year, and so decided to combine these two to provide a roundup of the best of both.
In our third roundup of 2018, we list the most popular blogs from our Credit Risk Management topic. Our credit risk blogs have mainly revolved around IFRS 9 and legislation changes this year, and have aimed to provide expert advice and insights into the current landscape.
For the second roundup of our most popular 2018 blogs, we cover the Data Analytics topic. The blogs that our readers love are thought-provoking and aim to inspire and teach – and we hope these articles do just that!
https://www.principa.co.za/contact-centre-solutions/artificial-intelligence-call-centre-virtual-assistant/We end off every year with a roundup of our most popular blogs – the blogs that you should not miss out on! This year is no different, and we'll be putting together four roundups this year, one for each of our main topics.
It isn't always easy to keep up-to-date with the latest news in data science, machine learning or artificial intelligence. Twitter is a great source of information and helps you quickly scan through headlines to engage with content that interests you. This helps eliminate a lot of noise and helps you focus on what you want to read about, but you need to follow the right people for that content to appear in your feed.
Meetup (www.meetup.com) was founded in 2002 and is an online service used to organise groups that host in-person events for people with similar interests. A social networking tool, unlike any other, Meetup, has more than 35 million users in 180 countries. In South Africa, there are many meetups organised for various interests. Of course, our interests span data science, machine learning and AI, so we took the time to put together a (non-comprehensive) list of the groups who organise meetups that we (and hopefully you) find of interest. We hope you make it out to one of these groups meetups soon!
We are approaching a time of the year when planning for 2020 takes centre stage. As such it is important to look back and asses the channels that have been used across contact centres and determine their effectiveness. At the same time, it is important to look ahead at the trends and customer behaviour which can help lead to better customer interactions and satisfaction.
We've been sharing our favourite machine learning books, podcasts and courses in the recent weeks, but we felt there was a glaring gap in the lists of resources we've been sharing: videos! Why did we think this is a noticeable gap? Because of these impressive statistics:
South Africa is currently the only country that has implemented an Early Debit Order (EDO) collection system. Our EDO system consists of both the AEDO (Authenticated Early Debit Order) and NAEDO (Non Authenticated Early Debit Order) payment streams and has been in use since 2006 to create a fair playing field for both businesses and consumers.
We’ve compiled this list of 10 people you should take note of in the machine learning field to keep yourself updated and informed about the field. It's also useful if you're interested in learning about machine learning, as these are the people who not only influence the industry but are paving the way forward and shaping the future of machine learning. We've given a short overview and a video to familiarise yourself with each of them, but if you're invested in learning about machine learning, follow them on social and start reading their publications.
Machine learning and artificial intelligence are exciting fields, and we've been writing about these topics for a couple of years now. While a lot of what we talk about on our blog is advanced implementations of machine learning and can be overwhelming to beginners, the core concepts of machine learning are actually pretty easy to grasp. There are many resources and cheat sheets available online, but we believe the old fashioned way of learning is sometimes the best: with a good book. Few resources can match the in-depth, comprehensive detail of a good book.
Our data scientists are keen readers and avid podcast listeners. In this blog, we list a few of the podcasts that cover topics such as data science, machine learning and artificial intelligence, and that we’d recommend if you’re looking to start exploring the world of podcasts.
In this blog, we’ve created a (non-exhaustive) list of courses you should consider if you want to learn essential data science skills in South Africa. These courses are mostly classroom training from South African institutions, but if you’re more interested in online learning, check out our blog Where To Learn Essential Data Science Skills Online.
We are quite proud of the ability to develop performant, stable and trustworthy predictive models here at Principa. For nearly 20 years, we have been developing predictive models that have helped so many of our clients to make better decisions, more often than not outperforming what our best competitors can achieve. The models that we have historically developed can be categorised as part of the additive group of models – that is, a handful of predictive characteristics are selected and classed in a way that best separates the ‘goods’ from the ‘bads' (i.e. the traditional binary classification application). Depending on the new unseen data, the resulting weightings are then added together to get a final score. For example, consider a 3-feature model that uses only Home Ownership, Years at Employer and Age. Let's say you are a homeowner and for this you get 10 points, you have been with your employer for 5+ years (15 points), and you are 23 years of age (8 points), then your final score is 33, and the strategy will use this score and decide where you should go in the business decision tree.
The value and benefits of becoming a data scientist or picking up basic data science skills, cannot be overstated in today’s world. Businesses across all industries are starting to embrace data analytics and those who aren’t will soon feel the advantage gained by their competitors who are.
How To Improve Your Call Centre Agent Performance from PrincipaDecisions
When we initially committed to being sponsors and exhibitors at the CEM Africa Summit, our team was very excited. Not only would we have a space on the floor that would give us the opportunity to meet and connect with attendees, but we’d also have the chance of exploring the sessions at this prestigious summit ourselves.
Learning rarely stops after your formal education ends, whether you’re pursuing further learning out of personal interest, career-aspiration or it’s mandated by your company. Most companies offer funding and support for their employees to go on courses to keep their skills up to date or learn new skills. Companies spend millions every year on enabling employees to participate in physical, often off-site training, and the costs can cover training fees, training material, travel and accommodation.
Answer your business questions with advanced business decisioning using DecisionSmart scoring, segmentation and decisioning engine to provide segmentation, scores and decisions based on your business data, and Agent X call centre virtual assistant to display information visually for optimal call centre agent performance.
Machine learning models can be used very successfully in many different contexts to predict outcomes for different use cases accurately. These predictions can be used within the business to make better decisions or to operate more efficiently (or both) and can give you an edge over your competitors. Predictive models all follow the same recipe – i.e. train a model on historical data and then apply this model to unseen data to get predictions. If your model generalises well, you have a prediction that you can trust and use to decide "do this, not that" with some degree of accuracy.
What is MarketWise? MarketWise is an audience of online users within South Africa which can be segmented and arranged according to a brand or advertisers target market. Online ads can then be served to this audience as they browse the internet.
We’ll be attending the first session of the CCMG’s Contact Centre Conference Tour in Johannesburg on the 22nd and 23rd of August. The conference tour will continue in September in Cape Town and in Durban in November.
A multinational luxury vehicle brand interested in promoting brand awareness through a display video banner were looking to increase action by improving campaign CTR at a lower CPC.
How To Identify And Pro-Actively Correct Operational Problems In Your Call Centre from PrincipaDecisions
When we started on our journey of predicting the results of the FIFA World Cup matches, we set out with some cautious optimism. We had experienced success with predicting the outcomes of the 2015 Rugby World Cup and the 2016 Oscars, but Football was a whole new ballgame. As our CEO, Jaco Rossouw, said: “We’ve never used our skills as data scientists to predict the outcomes of a football game, and unlike with the Rugby World Cup where we were predicting the point margins between the participating teams, this time we’ll be predicting the exact final scores - a significantly more complex challenge!”
After a FIFA World Cup full of upsets, the South African data scientists at Principa outranked 99.92% of people on popular sports predictor site, Superbru.
This year, we’re looking forward to adding a new conference to our calendar, as we head to the Customer Experience Management Africa Summit. This two-day summit is taking place on the 1st and 2nd of August at the Cape Town International Convention Centre.
As part of the group that was the second company worldwide to become IFRS9 compliant, IFRS9 has been at the forefront of what we do. We have assisted nearly 20 companies on their IFRS9 journey over the last two years. This blog forms part of a more extensive series on IFRS9.
Meet Vusi, a call centre agent, with call centre agent struggles. He needs to keep his customers engaged while he shifts between various systems to find the information he needs to meet his manager’s expectations of consistent, successful call outcomes.
If you're tasked with selecting a credit lifecycle software for your business, one of the most significant decisions facing you is whether to go with cloud-based or on-premise software. It's a question we get asked often, but the answer is often more complicated than an outright recommendation of one or the other. Each solution has pros, but also cons and therefore you’ll need to compare the two in-depth and select the option that suits your business strategy, and more importantly, your IT strategy.
As part of the group that was the second company worldwide to become IFRS9 compliant, IFRS9 has been at the forefront of what we do. We have assisted nearly 20 companies on their IFRS9 journey over the last two years. This blog forms part of a more extensive series on IFRS9. In this blog, we explore the administering of management overrides.
South African based data analytics company, Principa, will be predicting the results of every match at this year’s FIFA Football World Cup, to once again put theory into play. By applying the same principles used to predict customer behaviour for Principa’s financial services and retail clients, the company’s data scientists are using different algorithms to develop models that can predict the outcome of the matches.
Positioning is one of the most powerful marketing concepts a brand has at its disposal. (Click to Tweet!) Whether you’re a luxury vehicle designer or a value-based grocery store chain, you’ve likely spent a lot of resources perfecting and cementing your positioning, on your way to success.
The Simpson's Paradox is a phenomenon in statistics illustrating how easy it is to misinterpret data. (Click to Tweet!) It occurs mainly in descriptive and diagnostic analytics (see our blog on the different types of analytics) where an analyst may jump to a conclusion driven by motivated reasoning and not by objectively assessing the evidence.
The right customers are important for every business. Marketing to and serving customers who are not profitable removes your focus from your best customers and ensuring they remain loyal to your business. (Click to Tweet!) Scorecards can help you identify and focus on your ideal customers by ranking your customers by the common criteria historically shown to be shared by your best customers.
As part of our blog series on cognitive biases and logical fallacies that data scientists should avoid, today we address a prevalent logical fallacy: the "correlation proves causation" fallacy. Correlation due to causation is just one of the five main categories of causation, and this blog will look into each of the five.
In 2015, we predicted the Rugby World Cup to great success, out predicting 99.68% of humans. In 2016, we predicted the results of the Oscars, accurately predicting DiCaprio’s first win. This year we'll be trying our hand at predicting the outcomes of the FIFA Football World Cup, and we're cautiously optimistic about our predictions.
During the last year, we’ve experienced the escalation of social issues around artificial intelligence (AI), with Elon Musk leading the charge. Musk continues to advocate the idea that humanity is getting closer to a Skynet-like future – to many people’s concern. One of the very real and valid concerns is the idea that many existing jobs will be automated, thanks to AI.
For collection operations and risk alignment, a critical success factor is the ability to predict month-end results accurately and at an early stage of the billing cycle.
The Principa brand is unique and memorable as it is associated with creativity, integrity, innovation and deep expertise. Our website and blogs embodies every extraordinary aspect of our brand and we are very proud of it. We bring the same remarkable elements from this digital world, into our offices and into every interaction we have. Apart from the Principa team and our clients with whom we have an established relationship, not many people understand the elements that define our brand. I’d like to take this opportunity to introduce you to the wonders behind Principa.
Geo-location analytics, or location intelligence, is a powerful tool for marketers, developers and businesses in general. It’s defined as the analysis of IP address data to determine a user’s location, which gives a great deal of insight into the user, their behaviour and opportunities.
As Debt Collection and Recovery experts, we are given the opportunity to attend and present at industry conferences and events. We find the conferences incredibly valuable in helping us stay up to date, as well as challenging us to remain innovative.
According to this article by Frederick F. Reichheld in the Harvard Business Review, the average company loses about half its customers in a five-year period. When customers see a loss of value, they churn. The ultimate goal of a great loyalty strategy is to increase the perception of your solution’s value in the eyes of your customer, exactly when you need to. To achieve that, you need to be able to predict churn, many in the industry turn to leading (or lagging) indicators to indicate where efforts need to be focused.
“We must develop a comprehensive and globally shared view of how technology is affecting our lives and reshaping our economic, social, cultural, and human environments. There has never been a time of greater promise, or greater peril.” - Klaus Schwab, Founder and Executive Chairman, World Economic Forum (Click to Tweet!)
As a debt collection professional, there’s no doubt that you occasionally feel like you are out in the trenches. The nature of the industry is ever changing, as are the laws and regulations. And you need to stay on top of new technology and trends.
A Deep Learning IndabaX is a locally-organised, one-day Indaba that helps spread knowledge and builds capacity in machine learning. It's a way to experiment with how we can strengthen our machine learning community, and allow more people to contribute to the conversation.
A year ago, I published an article about motivated reasoning and how that can damage the data analytics process. It is part of a blog series on cognitive biases and logical fallacies that data analysts should avoid. Today I’d like to extend this conversation into a topical matter: p-hacking, also known as data fishing.
Whilst the journey to International Financial Reporting Standard 9 (IFRS 9) compliance has come at quite a cost to many credit-granting businesses, many are using the in-depth analytical exercise as an opportunity to make more informed decisions in their business. (Click to Tweet!)
Business Rules Management Systems (BRMS's) are the Swiss-army knives of business software. Despite this, very few companies we work with are getting the most out of their decision engines. In this blog, we explore how BRMSs are used across the customer lifecycle.
Does Proof of Income (POI) enable creditors to lend more responsibly? Or does it reduce the access to credit for many South Africans? Last week a controversial court ruling was passed effectively eliminating the requirement for proof of income documentation on credit applications in South Africa. In this blog, I take a look at how the initial POI regulation impacted consumers and the credit world, why and how the changes came about and what these new changes will mean to South-Africans.
An average customer’s attention span is less than that of a goldfish, according to the National Center for Biotechnology Information. While a goldfish can focus its attention for 9 seconds, in 2015 customers were found to lose interest after only 8, down from 12 seconds in 2000. (Click to Tweet!) The reduced attention span, makes the initial impression all the more critical, especially in a call centre environment.
With the release of the 2018 Predictions at the end of last year, Forrester forecast an uncertain fate for retailers who were laggards in digital transformation and those immune to obsessing over customer experience. One without the other will result in an equally disappointing outcome.
Geo-location analytics is defined as the analysis of IP address data to determine a user’s location. With geo-location being the new buzzword in marketing, brands who ignore this powerful tool risk losing out on a valuable way of reaching new customers.
Machine learning, for all its cool applications, is at its core the generation of predictive models using advanced algorithms that learn from data. If we have enough reliable and stable data to feed it, we can build models and make predictions on just about anything. If you are new to machine learning, read more on What is Machine Learning?
The fourth industrial revolution, much like the first three, has the potential to increase income levels and improve quality of life across the globe. Something to look forward to, but what exactly is it?
As the pressure of intensifying competition mounts every day, companies must look to boost customer loyalty, considering that it costs five times as much to onboard a customer than it is to retain one. And with consumer influence now stronger than ever, businesses that fail to respond to their customers’ needs will feel the impact on their sales figures. A recent study by Bain & Company revealed a 10% increase in customer retention levels results in a 30% increase in the value of a company, and a 5% increase in customer retention rates increases profits by between 25 and 95%.
We chat to Principa's Chief Executive Officer, Jaco Rossouw, about the thrilling new world of data and how businesses can work wonders with data-driven insights.
With direct marketing, you likely have a benchmark success rate from previous similar campaigns that you base your goals on, and you try to optimise it through various strategies, whether by trying to offer the best deals or by using behavioural tactics.
Data mining is another term that is often confused with machine learning (ML). Here’s an easy explanation of the two terms, as well as the relationship between the two.
Any tool that can optimise your collections strategy and improve efficiencies in your operation, is sure to make an impact on your collected yields. In our years helping collections operations to optimise and improve their collection strategies, we’ve found that data-driven debt collection tools offer the optimal solution to optimise and improve your recovery yields and increase your business revenue.
We have written a lot on ways to optimise your collection, but the simplest and most effective way is still to segment your debtors based on propensity to pay. Debtor segmentation is a best practice that every serious collections operation needs to utilise.
Machine learning and advanced data analytic techniques are often used in combination with behavioural sciences to develop coaching bots. Virtual assistant for call centre agents is a collections solution that guide and support agents through calls in real-time, offers them easy access to information and motivates and inspires high performance. This can translate directly to increased collection yields.
The management of debtors and account payments is often a laborious and reactive process that includes following up with debtors who are in default and don’t want to talk to you. Implementing a debt collections approach that is pro-active, could improve efficiencies and result in reduced amount of accounts rolling into delinquency.
With all the possibilities it presents, machine learning is on many a company’s to-do list for 2018. You could determine the optimal time and number to reach prospects and debtors on, improve cross-sell and upsell rates by offering the perfect next product at the perfect time or you can know when to give which customer a discount or special offer to prevent churn. But the costs of implementation of a machine learning tool in just one business area is high.
South African credit providers are heavily reliant on debit orders as a payment channel. According to the Payments Association of SA (PASA), around 48 million debit orders get processed monthly across all industries within the borders of this country. Of the two broad types of debit orders that we have, 33.5 million are standard debit orders, and 14.5 million are early debit orders. The early debit orders are further broken down into two types – being Non-Authenticated Early Debit Orders (NAEDO) and Authenticated Early Debit Orders (AEDO), with only around 1 million of the 14.5 million early debits being AEDO’s.
Machine learning has the power to transform the world, and it’s not just being used to power chatbots or to recommend your Netflix content. There are many amazing machine learning applications that improves our everyday live, but also makes the world a magical place.
The concept of artificial intelligence (AI) has been around for a while, but with the more recent rise of both machine learning (ML) and deep learning, it’s still a buzzword. These three are often used interchangeably, and thought of as the same thing. However, there is a significant difference between the three, which is valuable to know, especially when using the terms in conversation with people you want to impress!
Machine learning is a hot topic. Although we are interested in the inner workings of machine learning and how to improve our models, we are as interested in how to apply machine learning to improve business’ revenue and ROI. The positive impact on ROI through the application of machine learning techniques is well known to us. Based on our experiences, here are the most influential business applications of machine learning. These are the areas where we would recommend you start introducing ML in your consumer-focused business.
Can you test a different data-driven lead aqcuisition approach? Is it better to use one or multiple channels? Is this approach really successful? My team and I frequently get asked these and other questions on a data-driven approach to acquisition lead selection. In this blog, I’ll answer some of the most frequent questions.
There are many benefits to using a data-driven approach to lead selection, including higher conversion rates and improved ROI. In this second blog of our mini-series on using advanced data analytics in your acquisition strategy, we’ll discuss the data that will form the basis of your approach.
Every marketer is faced with a common challenge: improving conversion rates of your marketing campaigns whilst optimising marketing spend. This sounds straightforward (or so every non-marketer thinks), but is actually much easier said than done, at least when using traditional approaches.
I have the honour of curating the last of this year’s topic-specific Top Blog Collections. The blogs in my collection all focus on the customer, as we all should(!).
As we mentioned in our previous posts where we compiled lists of our top 2017 blogs, we are switching it up this year. Instead of compiling our usual list of Top 10 blog posts on data analytics, we are instead giving you a shorter, but more focused top blogs selection– and not just one, but five of them! Our data suggested that our most popular blogs were very clearly grouped in broad categories, and we’ve decided to give you the best Principa blogs of 2017, by topic.
Data science continues to be a hot topic in many large firms globally. 2017 saw data science subjects such as R vs. Python, deep learning, natural language, gamification, AI and machine learning being arguably the most topical.
As 2017 draws to a close, we reflect back on the year of credit. Some of the key themes that featured this year for us included:
Every year we compile a list of our Top 10 blog posts, to keep those who are out of the loop easily informed of the latest developments and thinking in data analytics. But in the interest of evolving and practicing what we preach, we are letting data inform the structure of our “Top Blogs” post this time around.
I have been lucky enough to work with and for various customer facing financial services organisations over the years. One of the benefits of this experience is the chance to compare and contrast how these organisations operate. Based on some of these observations, I have sketched out a generalised framework that describes the key functional actions of the modern customer-facing organisation. Meet the 3-I Raven*.
We've written many blog posts on the topic of Machine Learning and how it's improving everything from fraud prevention, direct marketing in retail and the customer experience in call centres to getting us to make more impulse purchases online and making holiday and business travel more enjoyable. It's with good reason we've given Machine Learning so much focus on our blog: it is a driving force in what the founder of the World Economic Forum - Klaus Schwab - is calling the Fourth Industrial Revolution. In this blog post we answer some frequently asked questions about Machine Learning, starting with what it is and how it relates to Artificial Intelligence.
As a company passionate about innovation we are regularly evaluating and re-evaluating knowledge – whether it’s our collective own, an employee’s or a client’s. Knowledge is a funny thing. Common sense might suggest that the more one learns about a subject the more confident one becomes. However, this is not entirely true, at least not in the beginning. The Dunning-Kruger Effect The Dunning-Kruger effect (DKE) is a cognitive bias that has been known for some time, but was only formalised in 1999 by two Cornell psychologists. It involves the seemingly contradictory idea that often those with little knowledge on a subject may come across as exceedingly confident about the subject. Conversely those with more knowledge may be less confident.
At Principa we’ve become quite passionate about Artificial Intelligence and Machine Learning. Recently quite a bit has been published in the press about how automated machines should be allowed to get. Most famously perhaps there have been the warnings from the likes of South African born Elon Musk and theoretical physicist Professor Stephen Hawking.
We have a bit of a joke in the office around how data scientists in 2027 will have a good laugh at what we define as ‘Big Data’ in 2017. Pat pat, there there, I guess that was Big Data back then. Unlike the term Big Data, Machine Learning is here to stay. It is after all one of the foundations of Artificial Intelligence and this is rapidly becoming more and more part of our culture. The impact of Machine Learning is being felt on a daily basis, from using interactive devices like Amazon’s Echo to do our shopping, learning a language through DuoLingo, or interacting with chatbots to get your statement in under a second instead of waiting “for the next available agent”. So what has happened, why the recent explosion of Machine Learning applications?
Most industries owe their levels of sophistication to the visionaries in their space. The South African credit industry is no different. Whilst the bureaux and the banks have played a significant role in developing the South African credit landscape, arguably the fashion retailers have also played a pioneering role in revolving credit. And so our vibrant industry owes much to the role of the fashion retailers. But how did it all begin?
When looking at the collections cascade and it’s diminishing returns, we always emphasis the responsibility factor relating to each metrics. Whom is responsible for these areas, and how do we monitor the accuracy of these metric results?
Today we explore some of the frequently asked questions around mathematical optimisation. For the most part the questions are answered in the context of credit risk. However mathematical optimisation and operations research in general have many applications.
Ever wondered how to calculate the best mix of actions in order to achieve the desired result within budget? You might have a pretty good idea of what mix has worked well in the past, but how much rigour goes into that process? Wouldn’t you like a mathematical approach that eliminates the guesswork?
Although not a new concept, very few credit-granting organisations have deployed a true multi-bureau strategy in their organisation. It is, however, talked about fairly regularly, but often dismissed as “too hard” or “not important enough”. So why should you consider a multi-bureau strategy? What are the key considerations? How do you go about deploying a multi-bureau strategy? This blog series will address these questions.
Here's a blog post covering some of the most frequently asked questions we get on Machine Learning and Artificial Intelligence, or Cognitive Computing. We start off with "What is Machine Learning?" and finish off by addressing some of the fears and misconceptions of Artificial Intelligence. So, what is machine learning? A simple search on Google for the answer will yield many definitions for it that leave most non-analytical people confused and entering more "What is..." statements into Google. So, I asked our Head of Marketing to try his hand at defining Machine Learning in the most simplistic way he can: explain Machine Learning to someone you've just met at a social gathering. Here's his definition - a "Machine Learning for Beginners' " definition if you will.
Seems like the term Machine Learning is popping up in mainstream media as the next big thing. The fact is, however, that Machine Learning went mainstream a long time ago. You don’t think so? Check your mobile phone. Chances are you’ve been using and benefiting from Machine Learning algorithms all this time without even knowing it. Read our opinion piece: Machine Learning Is Here To Stay In this blog post, I go through some of the many apps on your mobile phone that use Machine Learning algorithms to make recommendations, get you to your destination quickly and safely, improve your photos, tell you what song you’re listening to and more. You’ll see, Machine Learning is not so far away. It’s already in the palm of your hand. If you want to know what machine learning is, read our blog post on What is Machine Learning? And Other FAQs We Get...
The word optimisation is used quite loosely and can relate to many different areas. For example, there is search engine optimisation (getting your website pages to the top of online search results), process optimisation (making existing processes more efficient), code optimisation (making your code run more efficiently) and then there is mathematical optimisation. In this blog post, we'll be focusing on mathematical optimisation: what it is, how it can be applied in making more optimal business decisions at a customer level, and specifically how it's applied in credit risk. And you can even try using optimisation yourself - using an optimisation tool we've shared in this post - to see the various scenarios resulting from your decisions. Scroll to the bottom to try it for yourself!
A while back we published what we thought was a very informative blog post on the 4 types of data analytics. Our friends at KDnuggets - the industry's leading knowledge portal on Data Analytics and Machine Learning - re-posted our piece on their site last week and - lo and behold - it became the most read and most shared post on their site that week - over 2,300 reads and 8,500 shares on social media in less than a week. So, in case you missed it the first time we published it, read our post on the 4 Types of Data Analytics and see what everyone is tweeting about.
Believe it or not, we are halfway through 2017 and if you're feeling like you're no where near achieving what you set out to achieve this year, I'm sure you're not alone. But fear not! If one of your resolutions this year was to research how to apply data analytics or machine learning to your area of specialisation - be it Marketing, Customer Experience, Debt Collection or Risk Management - you still have time! And our Data Analytics Blog is a good place to start. I've looked at the stats and compiled our Top 10 list of most read blog posts for the first half of 2017. Check out our list of blog posts below and see what topics your colleagues and industry counterparts are researching this year:
I recently attended the First Party Summit – a Collections summit in the USA - which was an exciting conference focusing on the unique challenges of Collections, Outsourcing, and Customer Care. Over the 3-day period I learned quite a lot from the presentations and round table discussions covering topics from innovative communication strategies to the role of human and artificial intelligence in collections. Throughout the conference, I noticed the following two points were consistent through all aspects of the discussions: Personalisation and the Customer Experience are on the rise in debt collection. In this blog post, I’ll explain why.
Scorecards form the back-bone of decision making for many financial institutions. They are used in the account management of key decision areas like collections and authorisations, for example. They can tell us whether to accept or decline a customer for a particular credit based product, or tell us the percentage of a customer’s outstanding balance that will be recovered over a certain period of time. In this blog post, we’ll be covering what scorecard monitoring is, its importance and the consequences of not carrying out the exercise regularly.
Negotiation is a common activity in our daily lives. It’s human nature to try to influence others to achieve a better or advantageous outcome for ourselves. It’s ultimately an exchange of value. And if done well, it can leave both sides feeling like they’ve won. In my practice area of Collections & Recovery Solutions, negotiation is a critical tactic used in every engagement with a debtor. In fact, it’s so critical and core to the success of a Collections organisation that it merits a discussion with the ultimate negotiator to see if there are tips and techniques that can be learned and applied in Collections.
As a Marketer or Customer Engagement professional, imagine the cost-savings if you knew who in your database or lead list were likely to be the most profitable customers or most likely to respond? Would you bother mailing a list of a million contacts if you knew that only 100,000 of those contacts were worth targeting and very likely to respond? Innovation is not necessarily the invention of something new, but be the result of finding a new use for an existing product, service, methodology or practice. Take the use of predictive scoring in Marketing. Scoring is no longer only about identifying credit-worthy customers, but is now being used by marketers to identify "target-worthy" leads or customers.
The amount of data now available to us is overwhelming: every two days we create as much information as we did from the beginning of time until 2003. As a Marketer, the challenge is determining what data is useful and how to turn it into marketing wisdom that leads to customer retention and growth. Considering that it costs 5 times as much to on-board a customer than it is to retain one, companies would do well to leverage their data to develop and drive retention strategies. In this post, I look at 3 ways data can be used to build and drive customer retention strategies that result in reduced churn rates and open new avenues for meaningful engagement with target markets.
Effective communication helps us better understand and connect with those around us. It allows us to build trust and respect, and to foster good, long-lasting relationships. Imagine having this ability to connect with every customer (or potential customer) you interact with through communication that addresses their motivators and desires. In this blog post, I take a brief look at ‘customer segmentation’ and how it can foster the type of communication that leads to greater customer retention and conversion rates.
In this blog post, I will be covering some of the highlights from day 2 of the Finovate Spring Conference. Whereas the previous review of day 1 mostly covered innovations that assist the loans origination process, in this blog I’ll cover some of the analytical offerings. I’ll also cover some of the other offerings including training, investment platforms, and bot-based technology.
We at Principa decided to attend Finovate Spring again this year (we were here 2 years ago) to learn about new trends, network with like-minded companies and to look for potential partnerships. In this post, I cover some of the highlights and more interesting topics from Day 1 of the industry's most exciting gathering of innovators in the fintech world.
Being a company that’s so passionate about software and analytical innovation means that we must constantly keep our ear on the ground for new trends and products around the world. There is hardly a better place for innovation than California’s Silicon Valley. Over the next couple of days (26th - 27th April), I'll be live-tweeting from this year's Finovate Spring conference in San Jose, California and summarising my take from a data analytics perspective in blog posts at the end of each day.
Everyone is wanting to learn more about how machine learning can be used in their business. What’s interesting though, is that many companies may already be using machine learning to some extent without really realising it. The lines between predictive analytics and machine learning are actually quite blurred. Many companies will have built up some machine learning capabilities using predictive analytics in some area of their business. So if you use static predictive models in your business, then you are already using machine learning, albeit of the static variety.
McDonalds mastered the upsell with one simple question at the time of purchase: “You want fries with that?”. A simple and relevant question at the right time that has likely generated millions of extra dollars in revenue through the years for the company. Ever since then, companies have tried to emulate their success by identifying complementary products in their offering and training sales staff to ask customers the right question at the right time.
In our previous blog post we looked at data analytics in collections and the expected change in performance. Strategically, data analytics drives operational execution, but the question remains: where do we start? In this blog post, I outline the 3 steps to building your own data-driven collections strategy.
Use versus abuse of statistics can often be characterised by the analytical approach adopted to the problem at hand. In this blog post, which is part of a series on Logical Fallacies to avoid in Data Analysis, I’ll be focusing on defining the motivated reasoning logical fallacy and how to avoid it in data analysis.
The rise of Big Data, data science and predictive analytics to help solve real world problems is just an extension of science marching on. Science is humanity’s tool for better understanding the world. The tools that we use to build models, test hypotheses, look for trends to build value with our brand all derive directly from scientific principles. With these principles comes a myriad of obstacles. The obstacles are known to philosophers as “logical fallacies”, which I outlined in my previous post "The 7 Logical Fallacies to avoid in Data Analysis." In this blog post, we focus on the Texas Sharpshooter Fallacy and how to avoid it in your data analysis.
“Lies, damned lies and statistics” is the frequently quoted adage attributed to former British Prime Minister Benjamin Disraeli. The manipulation of data to fit a narrative is a very common occurrence from politics, economics to business and beyond.
If you’re involved in credit risk and existing customer marketing you’ll know that random numbers are frequently used when deploying different strategies. As strategies grow more complex and numerous, so the role of the random number grows more important. In this blog post, I’ll cover what randomisation is, why you should do it, when you should do it and what else to consider.
Credit lenders use data analytics to assess potential clients and determine affordability. However, many credit lenders and debt collection companies fail to apply the same practice when dealing with defaulting clients. In my first blog post, I'll cover the important role that data analytics can play in collections operations and solutions.
We've covered a few fundamentals and pitfalls of data analytics in our past blog posts. In this blog post, we focus on the four types of data analytics we encounter in data science: Descriptive, Diagnostic, Predictive and Prescriptive. Note: This blog post was published on the KDNuggets blog - Data Analytics and Machine Learning blog - in July 2017 and received the most reads and shares by their readers that month.
If I was to sum up our purpose at Principa, it would be “to help clients make informed decisions using data, analytics and software”. As information grows, so the opportunity to make better decisions increases. Data helps you understand your customer better. That’s our mantra. That’s our ethos. That’s why we are.
We take pride in our ability to predict - from the results of the 2015 Rugby World Cup and the 2016 Oscars to predicting profitable customers and customer churn. However, there is no denying that 2016 was a year full of shocking, unexpected events - from Brexit and the US election results to the acrimonious break-up of "Brangelina" (shocking!) and the sad loss of some very talented artists.
In this blog post I’ll be covering what bots are, how bots are used, the growing popularity of bots and the three types of bots that I have come across.
Machine Learning is by no means a new thing. Back in 1959, Arthur Samuel’s self-training checkers algorithm had already reached “amateur status” – no mean feat for that period in time. This article is intended to shed some light on the two different types of Machine Learning that one can encounter, which may be useful if you are thinking of entering into this space and are unsure as to which avenue is appropriate for your business.
Predictive Analytics can yield amazing results. The lift that can be achieved by basing future decisions from observed patterns in historical events can far outweigh anything that can be achieved by relying on gut-feel or being guided by anecdotal events. There are numerous examples that demonstrate the possible lift that can be achieved across all possible industries, but a test we did recently in the retail sector showed that applying stable predictive models gave us a five-fold increase in the take-up of the product when compared against a random sample. Let’s face it, there would not be so much focus on Predictive Analytics and in particular Machine Learning if it was not yielding impressive results.
Hands up who has not heard of R? If you are in the data analytics space and have an internet connection then you would have heard of the open source programming language for predictive analytics and statistical computing that has taken the analytics world by storm.
The International Accounting Standards Board published IFRS9 Financial Instruments in July 2014, a framework that introduces a number of new principles into bad debt provisioning that would require lenders to change the provisioning methodology and possibly some business practices in order to remain compliant.
Your customers go through numerous milestones in their journey through your business: the initial interest, the first purchase and opening of an account, (hopefully) paying their accounts on time, maybe signing up for your loyalty programme (and being comfortable to tell you more about themselves).
Machine learning is revolutionising how companies are capitalising on Big Data to develop their marketing strategies. While the term encompasses a broad spectrum of technologies and approaches, in a marketing context it can be used to improve targeting, response rates and overall marketing ROI. To put it simply, machine learning involves the automated analysis of large volumes of data – such as consumer spending habits and purchasing behaviour, as well as demographic information – and using a mathematical algorithm and a computer to identify patterns and trends. The algorithm then tests predictions based on historical campaign data and learns from the predictions it gets right. With time, these algorithms become highly accurate as more data from campaign results is added.
Thanks to mobile technology, wearable devices, social media and the general pervasiveness of the internet, an abundance of new customer information is now available to marketers. This data, if leveraged optimally, can create opportunities for companies to better align their products and services to the fluctuating needs of a demanding market space.
Luke Turnbull, Head of Customer and Lead Analytics at Principa, chats to South Africa's biggest Sunday news publication, the Sunday Times about the role consumer data plays in loyalty and reward programmes. According to Luke, harnessing customer data has become central to the success of loyalty and rewards programmes as customer data tells us who our customers are, how they behave, what motivates them, their needs and attitudes.
The power of Customer Experience and growing competition are driving companies to take a more scientific approach to building customer loyalty.
Credit companies are facing an increasingly volatile global financial climate. A person has to look no further than the impact the unexpected Brexit results have had on the global market. And if that’s not enough, the highly accelerated pace of technological development means that companies need to always be prepared to update their processes and methodologies to accommodate ever-changing client needs and to mitigate risk.
As developed countries experience a slow but steady recovery, credit risk managers in emerging markets face growing default rates as household debt continues to rise with little relief in sight. The Institute of International Finance stated at the end of 2015 that global household debt had risen by $7.7 trillion since 2007 to more than $44 trillion, and that $6.2 trillion of that rise was in emerging markets. Household debt per adult in emerging economies also rose by 120 percent over that period to some $3000, it added.
As the banking industry pursues improved customer engagement, unlocking the value of data becomes critical in designing a successful loyalty programme. The balance of power in banking has changed. What customers expect, how they want to be serviced, what information they are prepared to share, and how loyal they are prepared to be, have all changed radically. According to leading industry analysts, Forrester Research, we are in the age of the customer, in which the only sustainable competitive advantage is knowledge of and engagement with customers.
If you at all follow the on-goings of Hollywood, you’ve probably heard of a baseball movie starring Brad Pitt that came out a few years ago. Its name is Moneyball, and it relates an important lesson that is revolutionising customer engagement strategies. The movie tells the true story of Billy Beane, general manager of baseball team the Oakland Athletics, who’s sick and tired of their lacklustre performance. After a key loss to the New York Yankees, he’s forced to rebuild the team on a limited budget. Instead of going with the obvious picks, he enlists the help of a Yale economics graduate to crunch the numbers and pick a team of statistically strong yet undervalued players. After a few losses, the data-driven approach is proven effective when the Athletics go on to have a 20 game winning streak – the longest in the history of the game.
According to the World Bank, South Africans are the biggest borrowers in the world, with 86% of the population in debt.* And unfortunately, the National Credit Regulator, goes on to state that of the 20 million credit-active consumers in South Africa, 47% are in arrears on their accounts by three months or more, or had judgements against them, or had negative credit ratings on their credit record. ** As a credit risk professional, it is imperative to be able to segment your debtors by their propensity to roll and then apply the appropriate treatment by segment to minimise this risk and increase lift in your debt collection strategies.
South Africa’s First National Bank (FNB) has been considered one of the world’s most innovative financial institutions for years now. Voted the most innovative bank globally in 2012, the financial institution owns bragging rights as the first bank in South Africa to launch a mobile banking app in 2011 and second in line to provide fully-fledged web banking portal conveniences to its customers. For those who can remember the days before feature-rich banking apps, FNB also carved in-roads to making basic online services available to customers through SMS and WAP services - on what is now considered the archaic cell phones and internet backbones of the early 2000s.
Artificial intelligence (AI) and machine learning technology present an interesting meeting point between our fear of the unknown and our fear of being known (that is, fear of our private information being exposed and known by others). The erosion of privacy and rise of intelligent machines is actually a common theme in science fiction. But while reality still has a lot of catching up to do before we can call Skynet’s customer support or play cards with Agent Smith, many people have expressed genuine concern over the implications of modern technology – especially regarding their privacy.
Thanks to its broad applicability, data analytics has rapidly become a critical business function for modern organisations. But with expertise in the field in short supply and high demand, companies with an identified need for data analytics are looking beyond their traditional borders to monetise their information assets. Forrester Research predicts that a third of businesses will “pursue data science through outsourcing and technology” as organisations become less process-driven and look to their data to find new opportunities for innovation. And with globalisation and technological advancements making outsourcing a realistic and practical option for businesses, this trend is set to gain momentum. With this in mind, let's take a look at why an organisation would even consider outsourcing their analytics capabilities in the first place.
Machine learning is helping brands narrow the divide between their products and consumers in ways that would appear almost magical only ten years ago. From Amazon's personal product recommendations based on past purchases and browsing habits, to Netflix's uncanny ability to suggest just the right movie title according to your taste in film, data-driven insights are helping companies speak to individual customer preferences, who are demanding more personalisation in their products and engagements. This has moved data analytics from novelty status to an integral part of the marketing strategy, as brands discover new opportunities to communicate their unique selling points.
In his final keynote speech at the 2011 Apple Worldwide Developer’s Conference, Steve Jobs remarked that, “If the hardware is the brain and the sinew of our products, the software is its soul.” Jobs’ intimate understanding of and vision for his products stands out as one of the key reasons behind Apple’s success. His notoriously protective stance on his company vision and the extent of his involvement in the conception, design and development of his products right up until their anticipated release is legendary. But the man behind Forbes’ most valuable brand of 2015 also knew a little something about value creation and customer value management.
In order to improve customer loyalty, we need to listen to our customers more. Increasing our share of wallet and maximising customer lifetime value (CLV) will only happen when customers are prepared to choose our brands and products over our competitors. Fortunately, businesses are uncovering clues to improving customer loyalty in new places thanks to data and evolving analytics platforms. This led one bank in Canada to turn to the thousands of conversations between its representatives and its customers for new insights into elevating the customer experience.
Principa CEO Jaco Rossouw, speaks to ITWeb's Brainstorm Magazine, a publication aimed at the decision makers of the world, about the impact artificial intelligence will have on life as we know it, asking the pertinent question of whether machines can be taught how to reason.
Capacity management describes a company's ability to meet present and future demands for its products and services. This involves a wide set of roles, responsibilities, processes and functions that all depend on their successful execution and interplay between one another. Although the working parts are many, the end goal behind capacity management is a shared one: to beat the competition in delivering the best products and services to the customer.
Few take on a larger portion of the responsibility to steer their organisations to success than Risk Managers. And with fast-moving consumers, a globalised marketplace, unabated industry disruptions and shifts seemingly all occurring in unison, modern Risk Managers face a new set of challenges to that of their predecessors. But now, banks and other financial institutions are using historical customer transactional data to detect unusual activity on buyers' debit and credit cards to freeze transactions until purchases can be verified by the card owners.
The fact that you are a living, breathing, individual means you have a unique, human-shaped imprint. Be it radiation, the endless trail of dead skin cells, or your infinitesimal gravitational field, you’re leaving a mark that can potentially be reduced to a unit of data and analysed. Enter the human voice: each chortle and hum that emanates from a customer’s vocal chord is unique. This is especially apparent when their voices are converted to electrical signals over the phone – when speaking to your company’s contact centres, for example. And when patterns emerge, such as with certain emotions or excitement levels, intelligent programs can learn to identify human states of mind in real-time speech and act accordingly to improve the speaker’s experience.
Telematics is a relatively new field, combining telecommunications and vehicular technologies with the insights of information processing. While the term was coined in 1978 in a French government report on the rapid development of computer technology, it now nearly exclusively refers to the technology that tracks vehicles in real time using GPS. Through this technology, telematics companies have access to a large amount of data that, with the help of data analytics, can be extremely useful.
It’s been almost 15 years since we saw the future of crime prevention in “Minority Report” – but today, we are beginning to see those then fictitious yet fantastical methods of predicting and preventing crime being implemented in various parts of the world. I’ll briefly mention three examples below of how analytics is already being used to prevent crime today before going into more detail on a fourth example: using analytics to prevent a criminal from re-offending.
Corporate silos may have been necessary in a burgeoning industrial era some decades ago, but times have changed. The era of social, mobile, analytics and cloud (SMAC) technologies has been fuelling a new wave of business transformation. Virtually every industry is being affected by the SMAC phenomenon and we’re currently only scraping the surface of what is possible.
Shortly after the winners of the Oscars for Best Actor, Best Actress, Best Director and Best Picture were announced, John Robbie of Talk 702 spoke to Principa Data Scientist, Johan van Biljon, for a follow-up interview to find out how accurate Principa's predictions had been. Using data analytics, Principa correctly predicted Leo would win an Oscar for Best Actor, Brie Larson would win for Best Actress, and Iñárritu to win for Best Director.
John Robbie from Talk Radio 702 speaks to Principa Data Scientist, John Van Biljoen, about Principa's predictions for the Oscars this weekend. Principa's predictions are based on data analytics from over 80 years worth of Oscar winning movies.
We analysed 80 years of Oscars data to predict this year's Oscars winners. Along the way, we discovered some very interesting insights. Did you know 24% of Oscar winning films were based on a true story? Four of this year's Oscar nominees for Best Actor star in a film based on a true story. Is this a growing trend?
Spanish entertainment news website, Super Cartelera, picked up on the hype created by Principa around our predictions for this years Oscar nominees stating this might be the year Leo finally gets his Oscar. Apart from mentioning the other three nominees for Best Actress, Best Picture and Best Director, Super Cartelera found our infographic: "Oscars loves a True Story" particularly interesting highlighting that half of the movies nominated for an Oscar this year is based on a true story.
Data Scientist Tom Maydon speaks to CliffCentral host Gareth Cliff on how Principa used data analytics to predict the winners of the Oscars in the top four major categories.
Principa shares its predictions of who we think will win the 2016 Oscar Awards in the four major catergories with local technology news website ITweb. The data scientists at Principa have used data from hundreds of movies spanning back to 1935 to make these predictions.
Tech-savvy insight and analysis website Memeburn asks the question, can data analytics be used to predict who will win the Oscars and we believe we have the answer.
Times Live takes a look at who we predicted to win the Oscars this year based on Oscar data analysed from the past 80 years.
Read South African tech blog, HTXT.Africa, and their take on our Oscar predictions.
Following a highly successful initiative of using Machine Learning to predict last year’s Rugby World Cup results, we're trying our hand again at predicting the future and revealing some interesting insights along the way about another major event: The Academy Awards, or the Oscars.
Data has redefined how businesses understand their customer base and make decisions. For instance, it’s transformed marketing from a relatively intangible expense into a clear-cut investment with a measurable ROI and targetable initiatives. However, strategically applied data has more uses than strengthening your marketing efforts alone, especially when it comes to understanding your existing customers and better attending to their needs.
How does a credit card company differentiate itself in a market saturated with special offers, low interest rates, and convoluted rewards programs?
When you think of machine learning in action, it’s easy to imagine analytics-based marketing research or a matrix-style AI takeover. But there are actually far more grounded and practical applications that benefit hundreds of millions of people in their day-to-day leisure and business activities. Take the travel industry, for example. We’ve now reached a point in human history where over 100,000 flights are taking off every single day. With airports seeing more foot traffic than ever before – Dubai International alone saw over 78 million passengers in 2015 – they need to be run and managed like a carefully oiled machine. Alleviating bottlenecks is central to ensuring as smooth an operation as possible in the travelling experience.
In emerging or developing markets where formal credit history collection infrastructure or credit bureaus are lacking, the majority of people without reference data would struggle to achieve anything resembling an impressive credit score. As a large contingent of previously unbanked individuals join their respective middle classes in increasing numbers worldwide, lenders are finding creative ways of profiling and welcoming newcomers to the world of financial services.
The aim of a marketing director is simple: 1) to get your brand noticed by the right people and 2) to get the right people to choose it over your competitors’. As we all know, that task is becoming both more difficult and easier every day. With the rise of social media and mobile marketing it has become increasingly easy and cost-effective to reach a large audience. And the time required to do so has been cut dramatically. As a result, however, it has also become more difficult to compete for attention as the traditional barriers to building a brand, such as budget and geography, dissipate.
As the pressure of intensifying competition mounts, retailers and restaurateurs are looking to reduce costs across the supply chain while boosting customer loyalty. And with consumer influence now stronger than ever, businesses that fail to respond to the demand for improved products and services will feel the impact on their sales figures. Central to this is the pervasiveness of the social, mobile, analytics and cloud (SMAC) era that is redefining traditional retail models that place the consumer at centre-stage.
I fondly remember watching as a child “The Roadrunner Show” cartoon series where the coyote (Wile E. Coyote) was devising elaborate schemes to try and catch the roadrunner. Although his schemes appeared to be clever and creative (to a six year old at least), he always failed. So, in one of the episodes he ordered a giant mainframe type super computer (this was the 1950s after all) to apply “data science” to devise a more effective scheme. This time his prey was Bugs Bunny.
Machine learning is a subfield of data science that involves the use of algorithms and computing systems capable of learning on their own from new data as it becomes available, identifying patterns and automatically adapting to predict or anticipate future outcomes with an increasing degree of accuracy. For marketers, what this means is the ability to predict customer behaviour and make relevant and personalised offers on the fly to acquire, retain or grow your most profitable customers.
Traditionally, the first quarter of any calendar year sees a dilution of both collection and recovery yields given the overspend that occurs over the December holiday season. Therefore, optimal strategies and operational execution are key to mitigating the effects of the first quarter ‘hangover’.
We take a look at the Top Ten blog posts which received the greatest number of views in 2015.
In my previous post, we looked at the first “D” of the 3D approach of identifying and extracting value out of your transaction data: Determination. If you recall, I proposed a 3 step approach (the 3D approach) to realising value from a variety of large data sets: Determination –scour data sources to establish if and where there might be value Development – create models that will be developed for the decision areas where value was identified with data that is predictive of this predetermined outcome Deployment – implement and run the developed market
With the banking and credit industries still somewhat coping with paper and process-heavy cultures of yesteryear, innovation is fast becoming a key differentiating factor in attracting a new generation of customers. Thankfully, we live in an age where more can be done with relatively little effort thanks to the automation capabilities and extended reach technology provides us. This is why the mobile device is fast becoming the focal point of how people work, communicate, find entertainment, get informed or even transact.
Introducing scoring into your business, means the adoption of a reliable and feature-rich scoring and segmentation engine that can calculate predictions or make recommendations that will minimise risk and maximise return on investment. This guide will identify critical features and nice-to-haves when assessing a scoring engine.
In the first part of our series on "Finding Value in Transaction Data" we explored a problem that is encountered by many organisations – how to identify and extract value out of the ever growing amount of data.
Data analytics is certainly making its impact felt in our collective progress as a species, with the technology being applied across a wide range of human activity. A report by the United Nations entitled Humanitarianism in the Interconnected Age identifies four challenges surrounding data analytics in helping tackle global challenges such as access to education, natural disaster management and disease control and prevention. These requirements centre on the development, acquisition, analysis and sharing of the increasing numbers of new information channels to find solutions to global challenges. In this blog, we'll look at three ways data analytics is helping save lives by allowing us to understand, anticipate and manage events or situations that pose a threat to human life.
A scorecard is a mathematical model that is used to predict a certain outcome (for example the probability of default). The information used in a scorecard can vary, but common fields include demographic characteristics (e.g. age of applicant, number of dependants, time spent in current job) and credit bureau data (e.g. number of personal loans registered to applicant, worst arrears status on all account in the last 6 months).
The once flat region South of Johannesburg is littered with man-made yellow hillocks. These hills are a reminder of the history of Johannesburg – a city literally built on gold. The gold has been mined here since the rush of the 1880s. Much of the gold was extracted from the crushed rock and the left-overs transported by mules and later trucks to these locations. However, the mine-dumps (as they’re locally known) are yellow-coloured as a reminder that even after the original extract – allusive gold still exists in the waste piles.
With virtually every brand setting up shop on social media platforms these days, customers have become immune to seeing “just more marketing” come at them through their screens. But this isn't to say that social platforms don't have their place in omni-channel marketing. It simply means that maximising your online reach requires a little more than the odd tweet or like. Online communities are an ideal medium for brands to provide customers with a common base to share experiences, discuss news and trends and also discover new value in their brands in the process. South African online kitchenware store – and community - Yuppiechef is a primary example of a business that hit the community management nail on the head, and as a result, has grown into one of the most loved brands in South Africa.
Last month we used predictive analytics and machine learning to predict the results of the Rugby World Cup, “out-moneyballing” the bookies themselves and placing us at the top 00.32% of humans on sports prediction site, SuperBru. Now that the dust has settled a bit after that fun initiative, I thought I’d look into other ways data analytics is being used in the sports world today. There are indeed many ways, but for the sake of brevity, let’s look at four of the more interesting ways that data analytics is changing the world of sports.
Julian Diaz, Head of Marketing for Principa, joins SAP and SAS in speaking to ITWEB about how data analytics and Big Data are transforming the world of sports.
Tech-savvy news website Memeburn, interviews Principa for "The Tech Behind," a new podcast series that looks at the innovative ways in which tech is being used in our everyday lives. In this first podcast, Principa shares the methodology, data sources and principles used to predict the rugby and the challenges and lessons learned.
With marketing budgets increasingly stretched to cover the myriad of channels and touch points out there today, CMOs might feel a little uncertain about whether they’re focusing on the right areas for their acquisition strategies. But even if your marketing spend does deliver positive on-boarding results, it’s still only the first step in a much longer journey with your customer. With the cost of acquiring new business usually five times more expensive than retaining existing customers, and with over 60% of revenue coming from existing customer bases, it only makes sense to build watertight retention strategies that not only retain customers, but preserve the best among them.
It seems to be a topic of conversation everywhere you go, and now the Internet of things (IoT) and a growing data-sharing culture is helping make the world a safer place - one missing drain cover and pothole at a time.
It was Wendell Smith, president of The Marketing Science Institute at the time, who in 1956 first advocated customer segmentation as a means to drive market demand, influence brand preference, and improve overall marketing profitability. Smith’s observations in this now 66 year old Journal of Marketing piece still holds some views that are largely relevant to today’s marketing landscape.
Lead Data Scientist at Principa Johan van Bijoen speaks to CNBC Africa about our Rugby World Cup predictions for the South Africa vs New Zealand semi-final and gives some brief insight into how the data used to make the predictions are derived. Watch the interview here
Listen to Gareth Cliff and Ben Karpinski of CliffCentral chatting to one of our data scientists looking at three possible ways of predicting the outcome of the Rugby World Cup Final: Man, Machine-Learning or Meowswers. Listen here 25 minutes into the clip.
Many of us remember the hoopla around the predicting ability of the now deceased FIFA World Cup predictor, Paul the Octopus. For those who don’t recall, Paul was an Octopus at a German aquarium that famously predicted with 100% accuracy the results of team Germany’s six matches and final match of the 2010 Soccer World Cup.
Despite our predictive analytics and machine learning predicting a loss for South Africa at this weekend’s Rugby World Cup semi-final against New Zealand, unpredictable variables such as missed penalties, wet weather, referee calls, and player strategy could result in an upset. This time, our team of data scientists hope our algorithms are wrong in their predictions. Read more here about how we came to these predictions.
Here's a quick catch-up we had this morning with John Robbie of Talk 702 to provide his listeners with our machine learning predictions for this weekend's Rugby World Cup semi-finals matches between New Zealand and South Africa and between Australia and Argentina. Listen here to our predictions for the semi-finals.
Since the early days of commerce, competing brands have grappled with how to be the one that comes to mind first when customers discover a “need” for a product. It is also fairly common knowledge that the cost of acquiring new customers is significantly higher than retaining the most valuable ones, highlighting the need to pre-empt the ebbs and flows of existing customer lifecycle stages and their respective segments as a means to optimise share-of-wallet. In the age of big data and predictive analytics, we’re getting much closer to reaching the level of brand awareness that helps us be present at the decisive moment our customers commit to the purchase.
Here's a follow-up to Friday's chat with Ben Karpinski and Gareth Cliff from CliffCentral about our prediction for a win for the Springboks by 4 points. Our use of Machine Learning and Predictive Analytics to predict the win resulted in a prediction that was spot-on. However, Ben's overall predictions for all 4 matches this past weekend were more accurate with him having predicted a win by Argentina against Ireland and our algorithms predicting the opposite. #ManVMachine-Learning: Ben 1, Principa 1 Listen here to Ben's analysis and chat with us here. Fast forward to minute 43.
Here's a follow-up to Friday's chat with John Robbie about our prediction for a win for the Springboks by 4 points. Our use of Machine Learning and Predictive Analytics to predict the win resulted in a prediction that was spot-on. Listen here to John Robbie's response to our spot-on perfect prediction.
Coverage by South Africa's largest IT website about our use of machine learning and predictive analytics to calculate the spot-on prediction of a win by the Springboks by four points this past weekend against Wales. Read the article here.
Listen to John Robbie of Talk 702 chatting to one of our data scientists about our use of Machine Learning and Predictive Analytics to predict the results of the Rugby World Cup matches. Listen here.
Listen to Gareth Cliff and Ben Karpinski of CliffCentral chatting to one of our data scientists about our use of Machine Learning and Predictive Analytics to predict the results of the Rugby World Cup matches. Listen here 11 minutes and 30 seconds into the clip.
The South African IT community lock in on our use of predictive analytics and machine learning to predict the outcome of the Rugby World cup quarterfinals this weekend. Read more here.
When we started our Man vs. Machine (Learning) initiative, we did so to have a bit of fun and to learn a few lessons we could apply to earning our bread and butter: predicting customer behaviour, customer lifetime value and credit worthiness, among other things, for our customers.
In my experience as a marketing professional, potential customers almost never just decide to walk away from a purchase - unless given sufficient reason to do so. And, if you’re wondering how a promising list of leads managed to slip through your fingers, it might be time to refocus on the basics of your on-boarding strategy.
Kevin Spacey may not have given data analytics the nod at his acceptance speech this year at the Golden Globes, but that doesn’t mean the star doesn’t understand the depth of data’s role in the success of his hit show, House of Cards.
A great interview with South Africa's leading online community for Marketing, Loyalty and PR professionals. The interview is with our CEO and his take on our Rugby World Cup predictions using machine learning and predictive analytics. Some excellent questions posed by journalist Leigh Andrews! Read the full interview here
South Africa's oldest newspaper, The Herald, gets the insights on how our data scientists are using predictive analytics and machine learning to generate Rugby World Cup predictions that are "on the mark." Read the full article here.
The readers of tech-savvy online publications today read about our ability to predict the results of the Rugby World cup matches with high accuracy using machine learning and predictive analytics. Read the full story here.
South Africa's The Daily Dispatch states that Principa's data scientists' use of machine learning and predictive analytics to predict the Rugby World Cup are giving the bookies a run for their money! Read the full article here.
We created some nice infographics with cool stats about the upcoming South Africa vs. Scotland match, and another one just for the Springboks. Great to see them getting picked up and cited by a publication we love to read: The Daily Maverick.
Our predictions are getting national attention as our standing in sports prediction site, Superbru.com, have beat 99.5% of everyone else on SuperBru. Love the headline! Read the story online here in The Times Live
The South African IT community read about our use of machine learning and predictive analytics to predict a victory for South Africa over Scotland in this weekend's Rugby World Cup match between the two teams. Read more here.
Online publication for globally minded South Africans, The South African, published our story of how we initially predicted the Japan vs. South Africa upset at the start of the Rugby World Cup. Read the full story here.
On Friday morning, 25 September, we spoke with South African radio personalities Gareth Cliff and Ben Karpinski (@followthebounce) on Internet radio station CliffCentral.com about the use of our algorithms and machine learning to predict the outcome of the rugby matches during the Rugby World Cup.
It’s Man vs. Machine at Principa HQ as our data scientists apply predictive analytics and machine learning to predict the winners and spread of each match during the Rugby World Cup. We signed up two internal teams of data scientists onto sports prediction site SuperBru.com as an exercise to put theory into play in this year’s Rugby World Cup. By applying the same principles used to predict customer behaviour for our financial services and retail clients, our two teams are vying against each other to develop algorithms and predictive models that can predict the outcome of the matches with the highest accuracy.
It’s Man vs. the Machine as South African based data analytics company, Principa, apply predictive analytics and machine learning to predict the winners and spread of each match during the Rugby World Cup. South African based data analytics company, Principa, have signed up two internal teams of data scientists onto sports prediction site SuperBru.com as an exercise to put theory into play in this year’s Rugby World Cup. By applying the same principles used to predict customer behaviour for the company’s financial services and retail clients, two teams of data scientists are vying against each other to develop algorithms and predictive models that can predict the outcome of the matches with the highest accuracy.
At Forrester Research’s Groundswell for Excellence in Social Media Awards ceremony held in April this year, winners were recognised for their innovative use of social media to drive awareness of their brands, delight customers with quality content, and reach more people than could ever have been possible in a world without tweets and shares. I’ve been somewhat puzzled by talk of social media, as a marketing platform at least, being on its last legs. The way I see it is that social is only shifting into higher gear and looking at how this year’s Forrester Research winners leveraged the medium to up their relationship marketing game, social media is still very much alive and kicking. You can read more about this year’s winners and submissions here.
I don’t think any of us like it when someone forgets our name. Although anonymity might be the companion of choice for the most socially averse, for the rest of us, the feeling that we matter as individuals carries with it a sense of identity. Marketers who bear this fundamental human attribute in mind are already halfway to creating customer retention strategies that pay dividends. Don’t believe me? Then it might be worth mentioning the Coca-Cola “Share a Coke” campaign which replaced Coke’s universally recognised branding with the personal names of consumers. The result was almost 1 billion impressions on Twitter and over 150 million personalised bottles sold world-wide.
In the field of credit risk management, few would challenge data’s role in financial forecasting, lender analysis, credit-modelling and risk aversion. In short, credit risk managers are no strangers to data. But it could be argued that the value and volume of data they have access to largely determine the quality of their decision making. The shift towards more technology and data-centric business models has created new opportunities for those in the credit risk landscape to play more collaborative roles and engage other business divisions to produce positive outcomes in shorter time-spans.
Since the days of the first radio broadcast in 1922, it took a short span of only ten years for half of the American public to adopt the new medium of the time. Marketers soon caught on to the inherent opportunities in radio transmissions, and in 1922, the first radio advertisements were broadcast to millions of listeners. Today, we’re in a similar situation with data analytics rising in prominence and marketers shifting their strategies to become more pre-emptive in the way they engage consumers. Strangely, however, it seems that not all “modern marketers” are heeding the call for data-driven strategies. A Forrester Research survey concluded that out of over 500 B2B and B2C respondents, only 11% of marketers scored well enough to be categorised as modern, data-driven marketers.
In my eyes, loyalty programs exist for two simple reasons: to motivate increased engagement with your brand and to collect data in order to build deep customer understanding. But they also exist for a third reason: customers want them. In a study by Nielsen, 84% of respondents said they were more likely to choose retailers that offered a loyalty program. Forrester Research have found that 64% of consumers agree that loyalty programs influence where they make purchases, and 50% agree that loyalty programs influence what they buy.
Virtually every retailer or restaurant chain has some type of customer loyalty program these days. In South Africa, there are over 100 local loyalty programs with an estimated 50 million memberships across them. With this said, the challenge lies in building programs that appeal to each individual customer segment that result in increased spending on products and services while boosting loyalty to your brand - a big task in these competitive times. However, what is considered “value” by one customer isn’t necessarily perceived in the same way by the next.
Human psychology is a fascinating thing. As marketers, one of the many roles we play is of psychologist and, at times, of fortune teller. A good understanding of human behaviour and a high EQ are fundamental requirements for us to develop strategies and campaigns that will influence changes in perception and behaviour, and ultimately trigger an action: a click, a download, an email, a “Like,” a “follow” or a “retweet.”