Session-based Recommendations with Recurrent Neural Networks

Code

• github.com/microsoft/recommenders
  tf★ 21,541
• github.com/UlionTse/mlgb
  pytorch★ 1,049
• github.com/hidasib/GRU4Rec
  tf★ 801
• github.com/massquantity/LibRecommender
  tf★ 474
• github.com/yhs968/pyGRU4REC
  pytorch★ 149
• github.com/paxcema/KerasGRU4Rec
  tf★ 106
• github.com/hidasib/gru4rec_pytorch_official
  pytorch★ 75
• github.com/lmcRS/AWS-recommendation-papers
  none★ 60
• github.com/hidasib/gru4rec_tensorflow_official
  tf★ 6
• github.com/namthatman/Recommender-System
  none★ 0

Abstract

We apply recurrent neural networks (RNN) on a new domain, namely recommender systems. Real-life recommender systems often face the problem of having to base recommendations only on short session-based data (e.g. a small sportsware website) instead of long user histories (as in the case of Netflix). In this situation the frequently praised matrix factorization approaches are not accurate. This problem is usually overcome in practice by resorting to item-to-item recommendations, i.e. recommending similar items. We argue that by modeling the whole session, more accurate recommendations can be provided. We therefore propose an RNN-based approach for session-based recommendations. Our approach also considers practical aspects of the task and introduces several modifications to classic RNNs such as a ranking loss function that make it more viable for this specific problem. Experimental results on two data-sets show marked improvements over widely used approaches.

Tasks

Benchmark Results

Reproductions