An empirical study of next-basket recommendations

TL;DR

This paper conducts a systematic empirical evaluation of next-basket recommender systems, comparing various algorithms under uniform conditions to establish a fair assessment framework for future research.

Contribution

It introduces a unified evaluation framework for NBRs by applying multiple algorithms on consistent datasets and metrics, addressing previous methodological inconsistencies.

Findings

Identified strengths and weaknesses of existing NBR algorithms.

Provided a fair comparison of NBR methods under standardized settings.

Established a benchmark for future NBR research.

Abstract

Next Basket Recommender Systems (NBRs) function to recommend the subsequent shopping baskets for users through the modeling of their preferences derived from purchase history, typically manifested as a sequence of historical baskets. Given their widespread applicability in the E-commerce industry, investigations into NBRs have garnered increased attention in recent years. Despite the proliferation of diverse NBR methodologies, a substantial challenge lies in the absence of a systematic and unified evaluation framework across these methodologies. Various studies frequently appraise NBR approaches using disparate datasets and diverse experimental settings, impeding a fair and effective comparative assessment of methodological performance. To bridge this gap, this study undertakes a systematic empirical inquiry into NBRs, reviewing seminal works within the domain and scrutinizing their respective merits and drawbacks. Subsequently, we implement designated NBR algorithms on uniform datasets, employing consistent experimental configurations, and assess their performances via identical metrics. This methodological rigor establishes a cohesive framework for the impartial evaluation of diverse NBR approaches. It is anticipated that this study will furnish a robust foundation and serve as a pivotal reference for forthcoming research endeavors in this dynamic field.