FairTargetSim: An Interactive Simulator for Understanding and Explaining the Fairness Effects of Target Variable Definition
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_ | 1866912482136686592 |
|---|---|
| author | Gala, Dalia Phillips-Brown, Milo Goel, Naman Prunkl, Carinal Jubete, Laura Alvarez corcoran, medb Eitel-Porter, Ray |
| author_facet | Gala, Dalia Phillips-Brown, Milo Goel, Naman Prunkl, Carinal Jubete, Laura Alvarez corcoran, medb Eitel-Porter, Ray |
| contents | Machine learning requires defining one's target variable for predictions or decisions, a process that can have profound implications for fairness, since biases are often encoded in target variable definition itself, before any data collection or training. The downstream impacts of target variable definition must be taken into account in order to responsibly develop, deploy, and use the algorithmic systems. We propose FairTargetSim (FTS), an interactive and simulation-based approach for this. We demonstrate FTS using the example of algorithmic hiring, grounded in real-world data and user-defined target variables. FTS is open-source; it can be used by algorithm developers, non-technical stakeholders, researchers, and educators in a number of ways. FTS is available at: http://tinyurl.com/ftsinterface. The video accompanying this paper is here: http://tinyurl.com/ijcaifts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06031 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FairTargetSim: An Interactive Simulator for Understanding and Explaining the Fairness Effects of Target Variable Definition Gala, Dalia Phillips-Brown, Milo Goel, Naman Prunkl, Carinal Jubete, Laura Alvarez corcoran, medb Eitel-Porter, Ray Machine Learning Artificial Intelligence Computers and Society Machine learning requires defining one's target variable for predictions or decisions, a process that can have profound implications for fairness, since biases are often encoded in target variable definition itself, before any data collection or training. The downstream impacts of target variable definition must be taken into account in order to responsibly develop, deploy, and use the algorithmic systems. We propose FairTargetSim (FTS), an interactive and simulation-based approach for this. We demonstrate FTS using the example of algorithmic hiring, grounded in real-world data and user-defined target variables. FTS is open-source; it can be used by algorithm developers, non-technical stakeholders, researchers, and educators in a number of ways. FTS is available at: http://tinyurl.com/ftsinterface. The video accompanying this paper is here: http://tinyurl.com/ijcaifts. |
| title | FairTargetSim: An Interactive Simulator for Understanding and Explaining the Fairness Effects of Target Variable Definition |
| topic | Machine Learning Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2403.06031 |