Sequence-Aware Recommender Systems

TL;DR

This paper reviews sequence-aware recommender systems that utilize ordered user-item interactions over time, categorizes related tasks, summarizes algorithms, discusses benchmarking methods, and highlights open challenges in the field.

Contribution

It provides a comprehensive review and categorization of sequence-aware recommendation tasks, summarizes existing algorithms, and discusses benchmarking and open challenges.

Findings

Sequence-aware methods improve personalization by leveraging interaction order.

Existing algorithms vary in modeling sequential patterns and user behavior.

Benchmarking approaches are discussed to evaluate sequence-aware recommender systems.

Abstract

Recommender systems are one of the most successful applications of data mining and machine learning technology in practice. Academic research in the field is historically often based on the matrix completion problem formulation, where for each user-item-pair only one interaction (e.g., a rating) is considered. In many application domains, however, multiple user-item interactions of different types can be recorded over time. And, a number of recent works have shown that this information can be used to build richer individual user models and to discover additional behavioral patterns that can be leveraged in the recommendation process. In this work we review existing works that consider information from such sequentially-ordered user- item interaction logs in the recommendation process. Based on this review, we propose a categorization of the corresponding recommendation tasks and goals, summarize existing algorithmic solutions, discuss methodological approaches when benchmarking what we call sequence-aware recommender systems, and outline open challenges in the area.