From Variability to Stability: Advancing RecSys Benchmarking Practices
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917759490719744 |
|---|---|
| author | Shevchenko, Valeriy Belousov, Nikita Vasilev, Alexey Zholobov, Vladimir Sosedka, Artyom Semenova, Natalia Volodkevich, Anna Savchenko, Andrey Zaytsev, Alexey |
| author_facet | Shevchenko, Valeriy Belousov, Nikita Vasilev, Alexey Zholobov, Vladimir Sosedka, Artyom Semenova, Natalia Volodkevich, Anna Savchenko, Andrey Zaytsev, Alexey |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09766 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Variability to Stability: Advancing RecSys Benchmarking Practices Shevchenko, Valeriy Belousov, Nikita Vasilev, Alexey Zholobov, Vladimir Sosedka, Artyom Semenova, Natalia Volodkevich, Anna Savchenko, Andrey Zaytsev, Alexey Information Retrieval Artificial Intelligence Machine Learning 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. |
| title | From Variability to Stability: Advancing RecSys Benchmarking Practices |
| topic | Information Retrieval Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2402.09766 |