Hybrid Recommender System based on Autoencoders
Preprint
Abstract
A standard model for Recommender Systems is the Matrix Completion setting: given partially known matrix of ratings given by users (rows) to items (columns), infer the unknown ratings. In the last decades, few attempts where done to handle that objective with Neural Networks, but recently an architecture based on Autoencoders proved to be a promising approach. In current paper, we enhanced that architecture (i) by using a loss function adapted to input data with missing values, and (ii) by incorporating side information. The experiments demonstrate that while side information only slightly improve the test error averaged on all users/items, it has more impact on cold users/items.Keywords
All Related Versions
- Version 1, 2016-06-24, ArXiv
- Version 2, 2016-12-02, ArXiv
- Published version: , 11.
This publication has 5 references indexed in Scilit:
- Collaborative Deep Learning for Recommender Systems2015
- Social Popularity based SVD++ Recommender SystemInternational Journal of Computer Applications, 2014
- Reconstructing Missing Data in State Estimation With AutoencodersIEEE Transactions on Power Systems, 2011
- Matrix Factorization Techniques for Recommender SystemsComputer, 2009
- Nonlinear principal component analysis using autoassociative neural networksAIChE Journal, 1991