How Marketers Can Use Machine Learning To Boost Customer Loyalty
Posted by Luke Turnbull
September 12, 2016
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.
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.
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.
Luke Turnbull is the Head of Customer and Lead Analytics at Principa. He has worked in the financial services industry since 1995, during which time he has worked in process, strategy and operational design across a range of organisations in New Zealand, the United Kingdom and South Africa. Luke has been with Principa for 9 years and has led consulting engagements with Principa’s local retail clients across the customer lifecycle, with a particular focus on customer engagement and lead generation.