Attention-based mixture density recurrent networks for history-based recommendation

Tian Wang, Kyunghyun Cho, Musen Wen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recommendation system has been widely used in search, online advertising, e-Commerce, etc. Most products and services can be formulated as a personalized recommendation problem. Based on users' past behavior, the goal of personalized history-based recommendation is to dynamically predict the user's propensity (online purchase, click, etc.) distribution over time given a sequence of previous activities. In this paper, with an e-Commerce use case, we present a novel and general recommendation approach that uses a recurrent network to summarize the history of users' past purchases, with a continuous vectors representing items, and an attention-based recurrent mixture density network, which outputs each mixture component dynamically, to accurate model the predictive distribution of future purchase. We evaluate the proposed approach on two publicly available datasets, MovieLens-20M and RecSys15. Both experiments show that the proposed approach, which explicitly models the multi-modal nature of the predictive distribution, is able to greatly improve the performance over various baselines in terms of precision, recall and nDCG. The new modeling framework proposed can be easily adopted to many domain-specific problems, such as item recommendation in e-Commerce, ads targeting in online advertising, click-through-rate modeling, etc.

Original languageEnglish (US)
Title of host publication1st International Workshop on Deep Learning Practice for High-Dimensional Sparse Data
Subtitle of host publicationBridging Theory and Practice, DLP 2019 with KDD 2019
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450367837
DOIs
StatePublished - Aug 5 2019
Event1st International Workshop on Deep Learning Practice for High-Dimensional Sparse Data: Bridging Theory and Practice, DLP-KDD 20'19 - Anchorage, United States
Duration: Aug 5 2019 → …

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference1st International Workshop on Deep Learning Practice for High-Dimensional Sparse Data: Bridging Theory and Practice, DLP-KDD 20'19
CountryUnited States
CityAnchorage
Period8/5/19 → …

    Fingerprint

Keywords

  • Deep learning
  • Mixture density network
  • Personalization
  • Recommender system
  • Recurrent neural network

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Wang, T., Cho, K., & Wen, M. (2019). Attention-based mixture density recurrent networks for history-based recommendation. In 1st International Workshop on Deep Learning Practice for High-Dimensional Sparse Data: Bridging Theory and Practice, DLP 2019 with KDD 2019 [3341254] (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). Association for Computing Machinery. https://doi.org/10.1145/3326937.3341254