A Troubling Analysis of Reproducibility and Progress in Recommender Systems Research

TL;DR

This paper critically examines recent neural recommender system research, revealing that most complex models do not outperform simple baselines, highlighting issues in research practices and questioning claimed progress.

Contribution

It provides a reproducibility analysis of neural recommendation approaches, exposing that many do not surpass simple methods and discussing research practice issues.

Findings

Most neural approaches are outperformed by simple heuristics

Complex neural models are not consistently better than traditional methods

Research stagnation due to methodological issues

Abstract

The design of algorithms that generate personalized ranked item lists is a central topic of research in the field of recommender systems. In the past few years, in particular, approaches based on deep learning (neural) techniques have become dominant in the literature. For all of them, substantial progress over the state-of-the-art is claimed. However, indications exist of certain problems in today's research practice, e.g., with respect to the choice and optimization of the baselines used for comparison, raising questions about the published claims. In order to obtain a better understanding of the actual progress, we have tried to reproduce recent results in the area of neural recommendation approaches based on collaborative filtering. The worrying outcome of the analysis of these recent works-all were published at prestigious scientific conferences between 2015 and 2018-is that 11 out of the 12 reproducible neural approaches can be outperformed by conceptually simple methods, e.g., based on the nearest-neighbor heuristics. None of the computationally complex neural methods was actually consistently better than already existing learning-based techniques, e.g., using matrix factorization or linear models. In our analysis, we discuss common issues in today's research practice, which, despite the many papers that are published on the topic, have apparently led the field to a certain level of stagnation.