Session-based Recommendations with Recurrent Neural Networks
B. Hidasi, A. Karatzoglou, L. Baltrunas, and D. Tikk. (2015)cite arxiv:1511.06939Comment: Camera ready version (17th February, 2016) Affiliation update (29th March, 2016).
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.
Description
Session-based Recommendations with Recurrent Neural Networks
%0 Generic
%1 hidasi2015sessionbased
%A Hidasi, Balázs
%A Karatzoglou, Alexandros
%A Baltrunas, Linas
%A Tikk, Domonkos
%D 2015
%K recommendation rnn session toread web
%T Session-based Recommendations with Recurrent Neural Networks
%U http://arxiv.org/abs/1511.06939
%X 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.
@misc{hidasi2015sessionbased,
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.},
added-at = {2016-11-01T19:10:41.000+0100},
author = {Hidasi, Balázs and Karatzoglou, Alexandros and Baltrunas, Linas and Tikk, Domonkos},
biburl = {https://www.bibsonomy.org/bibtex/2565a9cad04a1efeedcfb42f49c797ded/hotho},
description = {Session-based Recommendations with Recurrent Neural Networks},
hallo = {Weltweittoll},
interhash = {345864da98e60fa98719ba1118322ffe},
intrahash = {565a9cad04a1efeedcfb42f49c797ded},
keywords = {recommendation rnn session toread web},
note = {cite arxiv:1511.06939Comment: Camera ready version (17th February, 2016) Affiliation update (29th March, 2016)},
timestamp = {2016-11-03T10:56:08.000+0100},
title = {Session-based Recommendations with Recurrent Neural Networks},
url = {http://arxiv.org/abs/1511.06939},
year = 2015
}