SDM: Sequential Deep Matching Model for Online Large-scale Recommender System

Abstract

Capturing users' precise preferences is a fundamental problem in large-scale recommender system. Currently, item-based Collaborative Filtering (CF) methods are common matching approaches in industry. However, they are not effective to model dynamic and evolving preferences of users. In this paper, we propose a new sequential deep matching (SDM) model to capture users' dynamic preferences by combining short-term sessions and long-term behaviors. Compared with existing sequence-aware recommendation methods, we tackle the following two inherent problems in real-world applications: (1) there could exist multiple interest tendencies in one session. (2) long-term preferences may not be effectively fused with current session interests. Long-term behaviors are various and complex, hence those highly related to the short-term session should be kept for fusion. We propose to encode behavior sequences with two corresponding components: multi-head self-attention module to capture multiple types of interests and long-short term gated fusion module to incorporate long-term preferences. Successive items are recommended after matching between sequential user behavior vector and item embedding vectors. Offline experiments on real-world datasets show the superior performance of the proposed SDM. Moreover, SDM has been successfully deployed on online large-scale recommender system at Taobao and achieves improvements in terms of a range of commercial metrics.

arXiv comment9 pages, CIKM 2019 camera ready version

References in corpus (8)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Session-based Recommendations with Recurrent Neural Networks
• Regularizing and Optimizing LSTM Language Models
• Learning Tree-based Deep Model for Recommender Systems
• Learning from History and Present: Next-item Recommendation via Discriminatively Exploiting User Behaviors
• Next Item Recommendation with Self-Attention
• Deep Session Interest Network for Click-Through Rate Prediction
• A Long-Short Demands-Aware Model for Next-Item Recommendation

Cited by in corpus (8)

• Disentangling Long and Short-Term Interests for Recommendation
• Modeling Users' Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search
• Scenario-Adaptive and Self-Supervised Model for Multi-Scenario Personalized Recommendation
• Revisiting Neural Retrieval on Accelerators
• Triangle Graph Interest Network for Click-through Rate Prediction
• Entire Space Multi-Task Modeling via Post-Click Behavior Decomposition for Conversion Rate Prediction
• Denoising User-aware Memory Network for Recommendation
• Prototypical Contrastive Learning and Adaptive Interest Selection for Candidate Generation in Recommendations