Dynamic Collaborative Filtering with Compound Poisson Factorization
This work addresses the incremental improvement of recommendation systems for users and platforms by handling temporal dynamics in user-item interactions.
The paper tackled the problem of modeling drifting user preferences and item perceptions in collaborative filtering by proposing a dynamic matrix factorization model based on compound Poisson factorization with Gamma-Markov chains, achieving higher predictive accuracy on Netflix, Yelp, and Last.fm datasets compared to state-of-the-art static and dynamic models.
Model-based collaborative filtering analyzes user-item interactions to infer latent factors that represent user preferences and item characteristics in order to predict future interactions. Most collaborative filtering algorithms assume that these latent factors are static, although it has been shown that user preferences and item perceptions drift over time. In this paper, we propose a conjugate and numerically stable dynamic matrix factorization (DCPF) based on compound Poisson matrix factorization that models the smoothly drifting latent factors using Gamma-Markov chains. We propose a numerically stable Gamma chain construction, and then present a stochastic variational inference approach to estimate the parameters of our model. We apply our model to time-stamped ratings data sets: Netflix, Yelp, and Last.fm, where DCPF achieves a higher predictive accuracy than state-of-the-art static and dynamic factorization models.