A Bayesian Point Process Model for User Return Time Prediction in Recommendation Systems

Thomas, Sherin and Srijith, P K and Lukasik, M (2018) A Bayesian Point Process Model for User Return Time Prediction in Recommendation Systems. In: UMAP '18 Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization, 8-11 July 2018, Singapore.

Preview

Text
ACM Digital Library_1-2_2018.pdf - Submitted Version
Download (653kB) | Preview

Abstract

In order to sustain the user-base for a web service, it is important to know the return time of a user to the service. We propose a Bayesian point process, log Gaussian Cox process (LGCP), to model and predict return time of users. It allows encoding the prior do- main knowledge and non-parametric estimation of latent intensity functions capturing user behaviour. We capture the similarities among the users in their return time by using a multi-task learning approach. We show the effectiveness of the proposed approaches on predicting the return time of users to last.fm music service.

[error in script]

IITH Creators: