The approximation of a matrix by several lower-rank matrices is called matrix factorization. Matrix factorization methods are popular collaborative filtering methods, often with good scalability properties and predictive accuracy.
- Yehuda Koren, Robert Bell, Chris Volinsky: Matrix Factorization Techniques for Recommender Systems. IEEE Computer, 2009
- Rainer Gemulla, Peter Haas, Erik Nijkamp, Yannis Sismanis: Large-Scale Matrix Factorization with Distributed Stochastic Gradient Descent, KDD 2011