SplitLight: An Exploratory Toolkit for Recommender Systems Datasets and Splits

TL;DR

SplitLight is an open-source toolkit designed to analyze, compare, and improve the reproducibility of data splitting and preprocessing strategies in recommender system evaluations, addressing hidden biases and inconsistencies.

Contribution

It introduces a comprehensive toolkit that enables measurement, comparison, and diagnosis of data splits and preprocessing choices in recommender system datasets.

Findings

Detects temporal leakage and cold-start issues

Provides visual comparison of splitting strategies

Supports transparent and reproducible evaluation protocols

Abstract

Offline evaluation of recommender systems is often affected by hidden, under-documented choices in data preparation. Seemingly minor decisions in filtering, handling repeats, cold-start treatment, and splitting strategy design can substantially reorder model rankings and undermine reproducibility and cross-paper comparability. In this paper, we introduce SplitLight, an open-source exploratory toolkit that enables researchers and practitioners designing preprocessing and splitting pipelines or reviewing external artifacts to make these decisions measurable, comparable, and reportable. Given an interaction log and derived split subsets, SplitLight analyzes core and temporal dataset statistics, characterizes repeat consumption patterns and timestamp anomalies, and diagnoses split validity, including temporal leakage, cold-user/item exposure, and distribution shifts. SplitLight further allows side-by-side comparison of alternative splitting strategies through comprehensive aggregated summaries and interactive visualizations. Delivered as both a Python toolkit and an interactive no-code interface, SplitLight produces audit summaries that justify evaluation protocols and support transparent, reliable, and comparable experimentation in recommender systems research and industry.