Next Period Recommendation Reality Check

TL;DR

This paper evaluates the next-period recommendation task using a new large-scale financial transactions dataset, benchmarking existing methods and analyzing the challenges posed by repetitive consumption patterns in real-world data.

Contribution

Introduces TTRS, a large-scale financial dataset for NPR, and benchmarks popular RecSys approaches on this and other datasets, addressing reproducibility issues.

Findings

Repetitive consumption patterns are prevalent in real-world datasets.

Current RecSys methods struggle to generalize in repetitive data scenarios.

Item prediction performance remains limited in the NPR context.

Abstract

Over the past decade, tremendous progress has been made in Recommender Systems (RecSys) for well-known tasks such as next-item and next-basket prediction. On the other hand, the recently proposed next-period recommendation (NPR) task is not covered as much. Current works about NPR are mostly based around distinct problem formulations, methods, and proprietary datasets, making solutions difficult to reproduce. In this article, we aim to fill the gap in RecSys methods evaluation on the NPR task using publicly available datasets and (1) introduce the TTRS, a large-scale financial transactions dataset suitable for RecSys methods evaluation; (2) benchmark popular RecSys approaches on several datasets for the NPR task. When performing our analysis, we found a strong repetitive consumption pattern in several real-world datasets. With this setup, our results suggest that the repetitive nature of data is still hard to generalize for the evaluated RecSys methods, and novel item prediction performance is still questionable.