OverviewWith the ever-increasing advances in artificial intelligence and machine learning technologies, new levels of personalization have started to penetrate the rapidly growing world of e-commerce. We are helping companies collect information from countless channels (e.g., apps, emails, online platforms, on-site visits, phone calls), crossing this data, and finding the most relevant products for each customer.
ChallengeBPI wanted to create a platform to take advantage of the collected data through various channels. The growing number of possible messages/products to present made it difficult to handle using available segmentation rules.
OpportunityWe developed and deployed real-time machine learning algorithms able to analyze customers' trends in consumption and behaviors in order to recommend the most relevant products and services that the bank can offer.
To increase the number of active users and the level of engagement we also developed models to predict the churn of customers from the app. These models allow the support team to take different actions (e.g., push notifications, SMS, phone calls, and emails) according to the users' churn probability.