SplitLight: An Exploratory Toolkit for Recommender Systems Datasets and Splits
This addresses reproducibility and comparability issues for researchers and practitioners in recommender systems, though it is incremental as it provides a tool for existing evaluation challenges.
The paper tackles the problem of hidden, under-documented choices in data preparation for offline evaluation of recommender systems, which can undermine reproducibility and comparability, by introducing SplitLight, an open-source toolkit that analyzes dataset statistics, diagnoses split validity, and enables side-by-side comparison of splitting strategies.
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.