A key part of a recommender system is a collaborative filtering algorithm predicting users’ preferences for items. In this paper we describe different efficient collaborative filtering techniques and a framework for combining them to obtain a good prediction. The methods described in this paper are the most important parts of a solution predicting users’ preferences for movies with error rate 7.04% better on the Netflix Prize dataset than the reference algorithm Netflix Cinematch. The set of predictors used includes algorithms suggested by Netflix Prize contestants: regularized singular value decomposition of data with missing values, K-means, postprocessing SVD with KNN. We propose extending the set of predictors with the following methods: addition of biases to the regularized SVD, postprocessing SVD with kernel ridge regression, using a separate linear model for each movie, and using methods similar to the regularized SVD, but with fewer parameters. All predictors and selected 2-way interactions between them are combined using linear regression on a holdout set.
[1]
David Heckerman,et al.
Empirical Analysis of Predictive Algorithms for Collaborative Filtering
,
1998,
UAI.
[2]
Greg Linden,et al.
Amazon . com Recommendations Item-to-Item Collaborative Filtering
,
2001
.
[3]
Benjamin M. Marlin,et al.
Collaborative Filtering: A Machine Learning Perspective
,
2004
.
[4]
Kenneth Y. Goldberg,et al.
Eigentaste: A Constant Time Collaborative Filtering Algorithm
,
2001,
Information Retrieval.
[5]
Kamal Ali,et al.
TiVo: making show recommendations using a distributed collaborative filtering architecture
,
2004,
KDD.
[6]
Genevieve Gorrell,et al.
Generalized hebbian algorithm for incremental latent semantic analysis
,
2005,
INTERSPEECH.
[7]
Geoffrey E. Hinton,et al.
Restricted Boltzmann machines for collaborative filtering
,
2007,
ICML '07.
[8]
James Bennett,et al.
The Netflix Prize
,
2007
.