Probability-based Approach for Predicting E-commerce Consumer Behaviour Using Sparse Session Data

Abstract

This paper describes some of the key properties of the proposed solution for the RecSys 2015 Challenge from the team Tøyvind thørrud. Three contributions will be highlighted: i) Feature extraction, ii) Classifier design, and iii) Decision rules to optimize the prediction results towards the RecSys Challenge's score. We finished sixth out of more than 250 active teams in the competition.