Customer Behavior Analysis to Increase Online Purchase Rates

Summary

• Out client is one of the largest CPA networks in Eastern Europe.
• In the client’s business model, a gap between the payment from the CPA to affiliate and the payment from customer to CPA, gives a customer the time to change their mind about the purchase. The above leads to suppressed conversion purchase rates.
• We were challenged with reducing those revenue losses by analyzing the customer behavior on the web pages, predicting and preventing such cases.

Tech Challenge

• By using deep learning, our team first aimed to understand customer behavior and then model the probability of purchase based on user’s web-surfing experience.
• Those recommendations had to be revenue driven, maximizing profits of the service, while providing high quality services to a customer.
• Integration of our Apache Spark + Tensorflow architecture with clients Elastic + PostgreSQL + RabbitMQ.

Solution

• We’ve developed a detailed events tracking plan of customers activity and then tested the implementation against the historical data.
• The above helped to measure the most important behavioral patterns, correlating with customers purchase activity.
• Deep learning technologies helped us find the unintuitive correlations between users activity and purchasing outcomes, which are hard to find and interpret.

Impact

• Predicting the probability of both the purchase intent and actual purchase helped our client to prioritize calls queue and reduce the influence of bad traffic on the business by 16%.
• The solution also helped to optimize the customer journey on the website to prevent revenue losses from unrealized purchases.