Clustering algorithms and designing recommender systems for IceMobile

It has been a pleasure working with Xomnia. They are experts on the subject and very capable of explaining this knowledge to both technical and non-technical people within our company. Together we have been developing truly personalised promotions for our clients.
Thomas Hantke, Data Scientist

IceMobile is the market leader when it comes to digital loyalty campaigns within food retail. It combines data and digital research to deliver personalised mobile applications to increase customer loyalty and revenue for retailers worldwide. For one of its applications, IceMobile wanted to create customised promotions for each customer. The challenge here was to include all relevant factors for a good promotion such as, but limited to, transaction history, shopping behavior (e.g frequency, types of visits) and customer characteristics.

Together we have started to explore multiple solutions ranging from clustering algorithms to recommender systems. To assess the performance both on an aggregate level, as well as on an individual level, we have designed a framework and dashboard which allows for quick prototyping and shows key performance metrics for different types of algorithms. These algorithms were developed in a scalable and distributed manner to allow for food retailers with a worldwide presence. This system gives IceMobile the opportunity to create truly personalised promotions leading to better customer engagement and loyalty.