Plausible Counterfactual Explanations of Recommendations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912474677116928 |
|---|---|
| author | Černý, Jakub Němeček, Jiří Dovica, Ivan Mareček, Jakub |
| author_facet | Černý, Jakub Němeček, Jiří Dovica, Ivan Mareček, Jakub |
| contents | Explanations play a variety of roles in various recommender systems, from a legally mandated afterthought, through an integral element of user experience, to a key to persuasiveness. A natural and useful form of an explanation is the Counterfactual Explanation (CE). We present a method for generating highly plausible CEs in recommender systems and evaluate it both numerically and with a user study. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07919 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Plausible Counterfactual Explanations of Recommendations Černý, Jakub Němeček, Jiří Dovica, Ivan Mareček, Jakub Machine Learning Information Retrieval Explanations play a variety of roles in various recommender systems, from a legally mandated afterthought, through an integral element of user experience, to a key to persuasiveness. A natural and useful form of an explanation is the Counterfactual Explanation (CE). We present a method for generating highly plausible CEs in recommender systems and evaluate it both numerically and with a user study. |
| title | Plausible Counterfactual Explanations of Recommendations |
| topic | Machine Learning Information Retrieval |
| url | https://arxiv.org/abs/2507.07919 |