# Hybrid Recommender System based on Autoencoders Source: [Hybrid Recommender System based on Autoencoders]() Collection index: [llms.txt]() Data updated: 2026-01-04T02:48:22.396Z Authors: Florian Strub, Romaric Gaudel, J\\'er\\'emie Mary Published: 2016-06-24T12:37:04.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Rating Prediction on MovieLens 10M (90%/10%)](): Rating Prediction; MovieLens 10M (90%/10%); RMSE: 0.7754. - [Rating Prediction on MovieLens 20M (90%/10%)](): Rating Prediction; MovieLens 20M (90%/10%); RMSE: 0.7652. - [Rating Prediction on Douban](): Rating Prediction; Douban; RMSE: 0.6911. - [Rating Prediction on MovieLens 90/10 1M (train test)](): Rating Prediction; MovieLens 90/10 1M (train test); RMSE: 0.8316. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()