A Survey on Sequential Recommendation

TL;DR

This survey reviews recent advances in sequential recommendation, emphasizing new perspectives, techniques, and frontier topics to guide future research in understanding user preferences over item sequences.

Contribution

It introduces a novel perspective based on item properties and summarizes recent techniques and frontier topics in sequential recommendation research.

Findings

Summarizes recent techniques like ID-based, multi-modal, generative, and LLM-powered SR.

Highlights frontier topics such as open-domain, data-centric, and explainable SR.

Provides a comprehensive roadmap for future research in sequential recommendation.

Abstract

Different from most conventional recommendation problems, sequential recommendation focuses on learning users' preferences by exploiting the internal order and dependency among the interacted items, which has received significant attention from both researchers and practitioners. In recent years, we have witnessed great progress and achievements in this field, necessitating a new survey. In this survey, we study the SR problem from a new perspective (i.e., the construction of an item's properties), and summarize the most recent techniques used in sequential recommendation such as pure ID-based SR, SR with side information, multi-modal SR, generative SR, LLM-powered SR, ultra-long SR and data-augmented SR. Moreover, we introduce some frontier research topics in sequential recommendation, e.g., open-domain SR, data-centric SR, could-edge collaborative SR, continuous SR, SR for good, and explainable SR. We believe that our survey could be served as a valuable roadmap for readers in this field.