From Variability to Stability: Advancing RecSys Benchmarking Practices
Name
3637528.3671655.pdf
Size
1.69 MB
Format
Adobe PDF
Checksum (MD5)
11b9b9fa54d3853a2ace7d1372cf7d79
Author(s)
Shevchenko, Valeriy
Belousov, Nikita
Vasilev, Alexey
Zholobov, Vladimir
Sosedka, Artyom
Semenova, Natalia
Volodkevich, Anna
Savchenko, Andrey
Zaytsev, Alexey
Date Issued
August 25, 2024
Publisher
ACM|Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Citation
Shevchenko, Valeriy, Belousov, Nikita, Vasilev, Alexey, Zholobov, Vladimir, Sosedka, Artyom et al. 2024. "From Variability to Stability: Advancing RecSys Benchmarking Practices."
Version
Final published version
Abstract
In the rapidly evolving domain of Recommender Systems (RecSys), new algorithms frequently claim state-of-the-art performance based on evaluations over a limited set of arbitrarily selected datasets. However, this approach may fail to holistically reflect their effectiveness due to the significant impact of dataset characteristics on algorithm performance. Addressing this deficiency, this paper introduces a novel benchmarking methodology to facilitate a fair and robust comparison of RecSys algorithms, thereby advancing evaluation practices. By utilizing a diverse set of 30 open datasets, including two introduced in this work, and evaluating 11 collaborative filtering algorithms across 9 metrics, we critically examine the influence of dataset characteristics on algorithm performance. We further investigate the feasibility of aggregating outcomes from multiple datasets into a unified ranking. Through rigorous experimental analysis, we validate the reliability of our methodology under the variability of datasets, offering a benchmarking strategy that balances quality and computational demands. This methodology enables a fair yet effective means of evaluating RecSys algorithms, providing valuable guidance for future research endeavors.
Description
KDD ’24, August 25–29, 2024, Barcelona, Spain
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3637528.3671655
