Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.15274 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929396461338624 |
|---|---|
| author | Horowitz, Guy Sommer, Yonatan Koren, Moran Rosenfeld, Nir |
| author_facet | Horowitz, Guy Sommer, Yonatan Koren, Moran Rosenfeld, Nir |
| contents | When users stand to gain from certain predictions, they are prone to act strategically to obtain favorable predictive outcomes. Whereas most works on strategic classification consider user actions that manifest as feature modifications, we study a novel setting in which users decide -- in response to the learned classifier -- whether to at all participate (or not). For learning approaches of increasing strategic awareness, we study the effects of self-selection on learning, and the implications of learning on the composition of the self-selected population. We then propose a differentiable framework for learning under self-selective behavior, which can be optimized effectively. We conclude with experiments on real data and simulated behavior that both complement our analysis and demonstrate the utility of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_15274 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Classification Under Strategic Self-Selection Horowitz, Guy Sommer, Yonatan Koren, Moran Rosenfeld, Nir Machine Learning When users stand to gain from certain predictions, they are prone to act strategically to obtain favorable predictive outcomes. Whereas most works on strategic classification consider user actions that manifest as feature modifications, we study a novel setting in which users decide -- in response to the learned classifier -- whether to at all participate (or not). For learning approaches of increasing strategic awareness, we study the effects of self-selection on learning, and the implications of learning on the composition of the self-selected population. We then propose a differentiable framework for learning under self-selective behavior, which can be optimized effectively. We conclude with experiments on real data and simulated behavior that both complement our analysis and demonstrate the utility of our approach. |
| title | Classification Under Strategic Self-Selection |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.15274 |