The Road to Enlightenment: Generating Insight and Predicting Consumer Actions in Digital Markets

Abstract

E-commerce platforms are growing without stop nowadays. Lots of scientific research have been employed into the evolution of these platforms, a simple example is the recom- mendation engines that are now standard in electronic commerce websites. However, little to no effort has been made to determinate whether or not a given user is more or less prone to buy a product based on his previous actions. The goal of this dissertation is to design and develop an automatic approach for iden- tifying user behaviour, predicting their future actions throughout an website. Machine Learning techniques will be applied in order to learn from click-through logs data and predict user profitableness. Results will be studied and benchmarked in order to acknowledge the best approach to identify buying users.