A Collaborative Kalman Filter for Time-Evolving Dyadic Processes
Authors:
- San GultekinSGSan Gultekin
- John PaisleyJPJohn Paisley
- 1 December 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15504786,p. 140-149
Abstract
We present the collaborative Kalman filter (CKF), a dynamic model for collaborative filtering and related factorization models. Using the matrix factorization approach to collaborative filtering, the CKF accounts for time evolution by modeling each low-dimensional latent embedding as a multidimensional Brownian motion. Each observation is a random variable whose distribution is parameterized by the dot product of the relevant Brownian motions at that moment in time. This is naturally interpreted as a Kalman filter with multiple interacting state space vectors. We also present a method for learning a dynamically evolving drift parameter for each location by modeling it as a geometric Brownian motion. We handle posterior intractability via a mean-field variational approximation, which also preserves tractability for downstream calculations in a manner similar to the Kalman filter. We evaluate the model on several large datasets, providing quantitative evaluation on the 10 million Movie lens and 100 million Netflix datasets and qualitative evaluation on a set of 39 million stock returns divided across roughly 6,500 companies from the years 1962-2014.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Collaborative Kalman Filtering for Dynamic Matrix FactorizationIEEE Transactions on Signal Processing, 2014
- Dynamic matrix factorization: A state space approach2012
- Probability and Stochastics2011
- A spatio-temporal approach to collaborative filtering2009
- Matrix Factorization Techniques for Recommender SystemsComputer, 2009
- Exact Matrix Completion via Convex OptimizationFoundations of Computational Mathematics, 2009
- Graphical Models, Exponential Families, and Variational InferenceFoundations and Trends in Machine Learning, 2008
- Bayesian probabilistic matrix factorization using Markov chain Monte Carlo2008
- Item-based collaborative filtering recommendation algorithms2001
- On sequential Monte Carlo sampling methods for Bayesian filteringStatistics and Computing, 2000