Keynote: Session-Based Recommendation - Challenges and Recent Advances

In many applications of recommender systems, the system's suggestions cannot be based on individual long-term preference profiles, because a large fraction of the user population are either first-time users or returning users who are not logged in when they use the service. Instead, the recommendations have to be determined based on the observed short-term behavior of the users during an ongoing session. Due to the high practical relevance of such session-based recommendation scenarios, different proposals were made in recent years to deal with the particular challenges of the problem setting. In this talk, we will first characterize the session-based recommendation problem and its position within the family of sequence-aware recommendation. Then, we will review algorithmic proposals for next-item prediction in the context of an ongoing user session and report the results of a recent in-depth comparative evaluation. The evaluation, to some surprise, reveals that conceptually simple prediction schemes are often able to outperform more advanced techniques based on deep learning. In the final part of the talk, we will focus on the e-commerce domain. We will report recent insights regarding the consideration of short-term user intents, the importance of considering community trends, the role of reminders, and the recommendation of discounted items.