Characteristics of the Learning Data of a Session-Based Recommendation System and their Impact on the Performance of the System

Recommendation systems are an effective solution for personalising e-commerce services. They are able to provide customers with relevant and useful products. Their performance is determined by the quality of the methods employed. However, it is also influenced by the input data. Session-based (SB) techniques are highly effective in real-world scenario to generating recommendations that focus on short-term user activities. This study aims to investigate the relation between data statistics and performance of SB algorithms measured by accuracy and coverage.