Session-based recommendations with recurrent neural networks

Balázs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, D. Tikk

Research output: Contribution to conferencePaper

91 Citations (Scopus)

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.

Original languageEnglish
Publication statusPublished - Jan 1 2016
Event4th International Conference on Learning Representations, ICLR 2016 - San Juan, Puerto Rico
Duration: May 2 2016May 4 2016

Conference

Conference4th International Conference on Learning Representations, ICLR 2016
CountryPuerto Rico
CitySan Juan
Period5/2/165/4/16

Fingerprint

Recurrent neural networks
Recommender systems
neural network
Factorization
Websites
website
ranking
history
Recurrent Neural Networks

ASJC Scopus subject areas

  • Education
  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics

Cite this

Hidasi, B., Karatzoglou, A., Baltrunas, L., & Tikk, D. (2016). Session-based recommendations with recurrent neural networks. Paper presented at 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico.

Session-based recommendations with recurrent neural networks. / Hidasi, Balázs; Karatzoglou, Alexandros; Baltrunas, Linas; Tikk, D.

2016. Paper presented at 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico.

Research output: Contribution to conferencePaper

Hidasi, B, Karatzoglou, A, Baltrunas, L & Tikk, D 2016, 'Session-based recommendations with recurrent neural networks' Paper presented at 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, 5/2/16 - 5/4/16, .
Hidasi B, Karatzoglou A, Baltrunas L, Tikk D. Session-based recommendations with recurrent neural networks. 2016. Paper presented at 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico.
Hidasi, Balázs ; Karatzoglou, Alexandros ; Baltrunas, Linas ; Tikk, D. / Session-based recommendations with recurrent neural networks. Paper presented at 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico.
@conference{5e602359495c4c299359a896b2442a7d,
title = "Session-based recommendations with recurrent neural networks",
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.",
author = "Bal{\'a}zs Hidasi and Alexandros Karatzoglou and Linas Baltrunas and D. Tikk",
year = "2016",
month = "1",
day = "1",
language = "English",
note = "4th International Conference on Learning Representations, ICLR 2016 ; Conference date: 02-05-2016 Through 04-05-2016",

}

TY - CONF

T1 - Session-based recommendations with recurrent neural networks

AU - Hidasi, Balázs

AU - Karatzoglou, Alexandros

AU - Baltrunas, Linas

AU - Tikk, D.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85048469832&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048469832&partnerID=8YFLogxK

M3 - Paper

ER -