Collaborative Kalman Filtering for Dynamic Matrix Factorization

Abstract

We propose a new algorithm for estimation, prediction, and recommendation named the collaborative Kalman filter. Suited for use in collaborative filtering settings encountered in recommendation systems with significant temporal dynamics in user preferences, the approach extends probabilistic matrix factorization in time through a state-space model. This… (More)
DOI: 10.1109/TSP.2014.2326618

Topics

4 Figures and Tables

Statistics

0204060201520162017
Citations per Year

Citation Velocity: 19

Averaging 19 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.

Slides referencing similar topics