FairTargetSim: An Interactive Simulator for Understanding and Explaining the Fairness Effects of Target Variable Definition
This tool helps algorithm developers, stakeholders, researchers, and educators understand and mitigate fairness issues in target variable definition, though it is incremental as it builds on existing fairness simulation approaches.
The paper tackles the problem of fairness in machine learning by addressing biases in target variable definition, proposing FairTargetSim (FTS), an interactive simulator that demonstrates fairness effects using real-world data in algorithmic hiring.
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.