The Data Analytics Blog

Our news and views relating to Data Analytics, Big Data, Machine Learning, and the world of Credit.

All Posts

How Marketers Can Use Machine Learning To Boost Customer Loyalty

September 12, 2016 at 2:03 PM

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.

Read our "layman's" definition on What is Machine Learning?

However, the challenge of sorting through swathes of unstructured data to identify patterns and trends in customer behaviour and preferences can lead to a situation in which marketers are drowning in data without a single insight to show for it. And as any marketer will tell you, speed is of the essence to reach your customer at that moment of truth. Machine Learning is enabling marketers to “hyper-personalise” offers on an individual customer basis to boost customer loyalty.

Machine Learning enables hyper-targeting and optimal offers

As marketers, we’re all familiar with the use of customer data to segment our markets and personalise our engagement. But the reality is that we are limited by our own ability to process large amounts of data from various sources quickly, which results in us – at best – personalising at a group level, by segment rather than by individual. With the power of Machine Learning driving rewards and offers, marketers can now “hyper-target” and offer highly-personalised offers or rewards at an individual level - rather than at a group or segment level - at the right time, e.g. when the customer is browsing online or paying for their items at the till.

Machine learning uses mathematical algorithms and computing power to process much more data than humanly possible, taking data from various sources – such as transaction history, responses to campaigns, lifestyle segmentation, bureau data – and identifying patterns and trends, considering thousands of options before choosing the optimal offer that will most likely generate the desired response. What’s more the “learning” bit in Machine Learning means that the algorithm then remembers what offers resulted in a positive response and applies the same logic to a customer with a similar profile. Your “marketing machine” is then constantly learning and updating your rewards and offers to improve ROI on your loyalty programme. Machine Learning can be used to cross-sell and up-sell, predict and reduce churn, and improve customer segmentation by identifying groups of customers with similar traits and behaviours. Perhaps the best way to understand how to create a data-driven loyalty program is to see one in action.

Read how Marketers use Machine Learning to prevent Customer Churn.

A real-life example

A great example of machine learning informing a data-driven loyalty program can be found in Europe. Viseca Card Services SA is a Switzerland-based credit card company that also offers point-of-sale (PoS) terminals and payment solutions to merchants and vendors. Because of their unique position between both customer and vendor, they have access to highly valuable data pools. They draw on this advantage in their loyalty program, offering loyalty rewards to both sides of their customer base. Each card holder is automatically enrolled in the program, then encouraged to use it through recommendations, which are given based on an event-tracking system that monitors online events, like going to a certain retail site, clicking on a certain product or searching for a set of terms.

The system also tracks negative events, which are described as items that are shown to a user but not clicked on. The process is a closed loop, learning from every user interaction as well as factoring in demographic data, transaction history, preferences, etc. The loyalty program is designed around the input and analysis of this data, and uses both supervised and unsupervised learning techniques to model consumer behaviour and feed recommendations. This leads to a loyalty program that caters to a customer’s needs and improves their brand loyalty to the company’s partnered vendors.

Read how Marketers use Machine Learning to Upsell and Cross-Sell.

Machine learning enables marketers to hyper-target customers and offer the optimal offer that will boost brand loyalty, reduce churn and increase sales.

using data analytics for customer engagement

Image credit:

Luke Turnbull
Luke Turnbull
Luke Turnbull was the Head of Customer and Lead Analytics at Principa, until the end of 2017, after which he returned to his home country of New Zealand. He worked in the financial services industry since 1995, during which time he worked in process, strategy and operational design across a range of organisations in New Zealand, the United Kingdom and South Africa. Luke had been with Principa for 9 years and led consulting engagements with Principa’s local retail clients across the customer lifecycle, with a particular focus on customer engagement and lead generation.

Latest Posts

How chat is revolutionising the digital onboarding experience

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.

How to choose the correct collections chatbot

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. Click here to find out more. 

Model validation and adjustment

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.