Collaborative Recurrent Neural Networks for Dynamic Recommender Systems

Young-Jun Ko, Lucas Maystre, Matthias Grossglauser
Proceedings of The 8th Asian Conference on Machine Learning, PMLR 63:366-381, 2016.

Abstract

Modern technologies enable us to record sequences of online user activity at an unprece- dented scale. Although such activity logs are abundantly available, most approaches to recommender systems are based on the rating-prediction paradigm, ignoring temporal and contextual aspects of user behavior revealed by temporal, recurrent patterns. In contrast to explicit ratings, such activity logs can be collected in a non-intrusive way and can offer richer insights into the dynamics of user preferences, which could potentially lead more accurate user models. In this work we advocate studying this ubiquitous form of data and, by combining ideas from latent factor models for collaborative filtering and language modeling, propose a novel, flexible and expressive collaborative sequence model based on recurrent neural networks. The model is designed to capture a user’s contextual state as a personalized hidden vector by summarizing cues from a data-driven, thus variable, number of past time steps, and represents items by a real-valued embedding. We found that, by exploiting the inherent structure in the data, our formulation leads to an efficient and practical method. Furthermore, we demonstrate the versatility of our model by applying it to two different tasks: music recommendation and mobility prediction, and we show empirically that our model consistently outperforms static and non-collaborative methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v63-ko101, title = {Collaborative Recurrent Neural Networks for Dynamic Recommender Systems}, author = {Ko, Young-Jun and Maystre, Lucas and Grossglauser, Matthias}, booktitle = {Proceedings of The 8th Asian Conference on Machine Learning}, pages = {366--381}, year = {2016}, editor = {Durrant, Robert J. and Kim, Kee-Eung}, volume = {63}, series = {Proceedings of Machine Learning Research}, address = {The University of Waikato, Hamilton, New Zealand}, month = {16--18 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v63/ko101.pdf}, url = {https://proceedings.mlr.press/v63/ko101.html}, abstract = {Modern technologies enable us to record sequences of online user activity at an unprece- dented scale. Although such activity logs are abundantly available, most approaches to recommender systems are based on the rating-prediction paradigm, ignoring temporal and contextual aspects of user behavior revealed by temporal, recurrent patterns. In contrast to explicit ratings, such activity logs can be collected in a non-intrusive way and can offer richer insights into the dynamics of user preferences, which could potentially lead more accurate user models. In this work we advocate studying this ubiquitous form of data and, by combining ideas from latent factor models for collaborative filtering and language modeling, propose a novel, flexible and expressive collaborative sequence model based on recurrent neural networks. The model is designed to capture a user’s contextual state as a personalized hidden vector by summarizing cues from a data-driven, thus variable, number of past time steps, and represents items by a real-valued embedding. We found that, by exploiting the inherent structure in the data, our formulation leads to an efficient and practical method. Furthermore, we demonstrate the versatility of our model by applying it to two different tasks: music recommendation and mobility prediction, and we show empirically that our model consistently outperforms static and non-collaborative methods.} }
Endnote
%0 Conference Paper %T Collaborative Recurrent Neural Networks for Dynamic Recommender Systems %A Young-Jun Ko %A Lucas Maystre %A Matthias Grossglauser %B Proceedings of The 8th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Robert J. Durrant %E Kee-Eung Kim %F pmlr-v63-ko101 %I PMLR %P 366--381 %U https://proceedings.mlr.press/v63/ko101.html %V 63 %X Modern technologies enable us to record sequences of online user activity at an unprece- dented scale. Although such activity logs are abundantly available, most approaches to recommender systems are based on the rating-prediction paradigm, ignoring temporal and contextual aspects of user behavior revealed by temporal, recurrent patterns. In contrast to explicit ratings, such activity logs can be collected in a non-intrusive way and can offer richer insights into the dynamics of user preferences, which could potentially lead more accurate user models. In this work we advocate studying this ubiquitous form of data and, by combining ideas from latent factor models for collaborative filtering and language modeling, propose a novel, flexible and expressive collaborative sequence model based on recurrent neural networks. The model is designed to capture a user’s contextual state as a personalized hidden vector by summarizing cues from a data-driven, thus variable, number of past time steps, and represents items by a real-valued embedding. We found that, by exploiting the inherent structure in the data, our formulation leads to an efficient and practical method. Furthermore, we demonstrate the versatility of our model by applying it to two different tasks: music recommendation and mobility prediction, and we show empirically that our model consistently outperforms static and non-collaborative methods.
RIS
TY - CPAPER TI - Collaborative Recurrent Neural Networks for Dynamic Recommender Systems AU - Young-Jun Ko AU - Lucas Maystre AU - Matthias Grossglauser BT - Proceedings of The 8th Asian Conference on Machine Learning DA - 2016/11/20 ED - Robert J. Durrant ED - Kee-Eung Kim ID - pmlr-v63-ko101 PB - PMLR DP - Proceedings of Machine Learning Research VL - 63 SP - 366 EP - 381 L1 - http://proceedings.mlr.press/v63/ko101.pdf UR - https://proceedings.mlr.press/v63/ko101.html AB - Modern technologies enable us to record sequences of online user activity at an unprece- dented scale. Although such activity logs are abundantly available, most approaches to recommender systems are based on the rating-prediction paradigm, ignoring temporal and contextual aspects of user behavior revealed by temporal, recurrent patterns. In contrast to explicit ratings, such activity logs can be collected in a non-intrusive way and can offer richer insights into the dynamics of user preferences, which could potentially lead more accurate user models. In this work we advocate studying this ubiquitous form of data and, by combining ideas from latent factor models for collaborative filtering and language modeling, propose a novel, flexible and expressive collaborative sequence model based on recurrent neural networks. The model is designed to capture a user’s contextual state as a personalized hidden vector by summarizing cues from a data-driven, thus variable, number of past time steps, and represents items by a real-valued embedding. We found that, by exploiting the inherent structure in the data, our formulation leads to an efficient and practical method. Furthermore, we demonstrate the versatility of our model by applying it to two different tasks: music recommendation and mobility prediction, and we show empirically that our model consistently outperforms static and non-collaborative methods. ER -
APA
Ko, Y., Maystre, L. & Grossglauser, M.. (2016). Collaborative Recurrent Neural Networks for Dynamic Recommender Systems. Proceedings of The 8th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 63:366-381 Available from https://proceedings.mlr.press/v63/ko101.html.

Related Material