The Data Analytics Blog

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

All Posts

How Machine Learning Is Used In Marketing

January 11, 2016 at 3:59 PM

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.

Principa's own machine learning experiment during the 2015 Rugby World Cup received a lot of media attention thanks to the accuracy of our predictions. If you were following our posts and other media updates on our data-driven rugby predictions, you might be wondering how the application of machine learning within your business can lead to more accurate and profitable decision-making. The reality is that virtually any business stands to benefit from the big data boom.

Machine learning enables Marketers to anticipate customer behaviour

Marketers and rugby coaches face very similar challenges, in that both are heavily reliant on the analysis of a large, diverse group of individuals, their thinking processes and their predicted behaviour (or predicted performance when it comes to sports). Just ask our team of data scientists who sampled 6,000 rugby matches played by 99 teams over the past 20 years. But it was only through the convergence of such an impressive set of data that we were able to reach the top 0.32% in the popular online competition.

Marketers, by and large, already own large sets of customer and transaction data. By applying predictive models to these datasets, which can include campaign, transaction, response, on-boarding, social media and even sales data, marketers are able to gain foresight into how customers may respond to marketing, product or other stimuli they experience. But it doesn't stop there: as new data comes about through market engagement, marketing teams are able to make near real-time adjustments to campaigns and strategies and achieve better results through more personalised and targeted marketing.

Machine Learning prevents customer churn

There are numerous examples where Machine Learning has been used to great effect. One recent Harvard Business Review article uses a great example of a cable TV company that wants to identify subscribers that are likely to churn, and offer discounted rates to those at risk as a means to prevent churn. With no explicit data in hand to identify potential cancellations, the company subjects its customer database to a machine learning exercise known as a decision tree to separate potential defectors from those who will most likely remain loyal subscribers. The exercise incorporates customer behaviour, demographic, financial and other data to calculate - with very high probability - which way two sampled customers are likely to sway. Based on these insights, the company is then able to embark on a targeted customer retention campaign aimed at the right individuals.

What makes the example so interesting is the fact that it quite clearly illustrates how machine learning arrives at its predictions by factoring in many considerations derived from customer data that human beings could very easily – and probably do overlook.

Machine Learning automates up-sell and cross-sell

Some great real life examples of how machine learning helps up-sell and cross-sell include Amazon and Netflix’s automated recommendations of product or TV-series based on your purchase or viewing history. At both of these companies, algorithms and computer systems are learning from new data that it receives and making automated decisions based on it - no human intervention required.

Machine learning is basically automating the decision making process for marketers and enabling hundreds to thousands of decisions to be made in near real-time based on rapid data analysis and pattern recognition. And its power is only limited by the data at its disposal, which is good news for marketing teams who typically have a treasure trove of customer information in their possession. As the science develops over the coming months and years, so will new opportunities avail themselves for Marketers to bridge the gap between their brands and their customers. The only big concern will be their readiness to trust and act on the wisdom machine learning provides them.  

New call-to-action

Image credit: http://www.sailthru.com/

 

Robin Davies
Robin Davies
Robin Davies is the Head of Product Development at Principa. Robin’s team packages complex concepts into easy-to-use products that help our clients to lift their business in often unexpected ways.

Latest Posts

Amazon Web Services Vs Microsoft Azure: Which Cloud Provider Should You Host Core Business Systems On?

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.

Truth Seeker: How To Avoid Logical Fallacies And Cognitive Biases In Data Science

We have released a new eBook titled Truth Seeker: a guide to avoiding logical fallacies and cognitive biases in data science.

Exploring The Evolution Of Data Science In Banking

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.