{"type":"ScholarlyArticle","title":"Fairness-Aware Interactive Target Variable Definition","authors":[{"name":"Dalia Gala","slug":"dalia-gala","given":"Dalia","family":"Gala","affiliation":""},{"name":"Milo Phillips-Brown","slug":"milo-phillips-brown","given":"Milo","family":"Phillips-Brown","affiliation":""},{"name":"Naman Goel","slug":"naman-goel","given":"Naman","family":"Goel","affiliation":""},{"name":"Carina Prunkl","slug":"carina-prunkl","given":"Carina","family":"Prunkl","affiliation":""},{"name":"Laura Alvarez Jubete","slug":"laura-alvarez-jubete","given":"Laura","family":"Alvarez Jubete","affiliation":""},{"name":"medb corcoran","slug":"medb-corcoran","given":"medb","family":"corcoran","affiliation":""},{"name":"Ray Eitel-Porter","slug":"ray-eitel-porter","given":"Ray","family":"Eitel-Porter","affiliation":""}],"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.","doi":"10.24963/ijcai.2025/1260","url":"https://ijcai.org/proceedings/2025/1260","pdf":"https://ijcai.org/proceedings/2025/1260.pdf","markdown":"https://ijcai.org/proceedings/2025/1260.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/1260","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Demo Track","track":"Demo Track","number":1260,"pages":{"first":11048,"last":11052},"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"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}