Proceedings

Fairness-Aware Interactive Target Variable Definition

Dalia Gala, Milo Phillips-Brown, Naman Goel, Carina Prunkl, Laura Alvarez Jubete, medb corcoran, Ray Eitel-Porter

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Demo Track. Pages 11048-11052.

https://doi.org/10.24963/ijcai.2025/1260

Keywords

  • AI Ethics, Trust, Fairness: ETF: Fairness and diversity
  • Humans and AI: HAI: Human-computer interaction
  • AI Ethics, Trust, Fairness: ETF: Moral decision making
  • AI Ethics, Trust, Fairness: ETF: Bias

Abstract

Machine learning requires defining one's target variable for predictions or decisions, a process that can have profound implications on fairness, since biases are often encoded in target variable definition itself, before any data collection or training. The downstream impacts of target variable definitions must be taken into account in order to responsibly develop, deploy, and use the algorithmic systems. We propose FairTargetSim (FTS), an interactive and simulations-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.

Dalia Gala, Milo Phillips-Brown, Naman Goel, Carina Prunkl, Laura Alvarez Jubete, medb corcoran, and Ray Eitel-Porter. 2025. Fairness-Aware Interactive Target Variable Definition. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 11048–11052. https://doi.org/10.24963/ijcai.2025/1260
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards