À Propos

The increasing use of algorithmic decision making in domains that affect people’s lives such as employment, education, policing and loan approval, has raised concerns about possible biases and discrimination that such systems might introduce. Recent concerns about algorithmic discrimination have motivated the development of fairness-aware mechanisms in the machine learning (ML) community and the operations research (OR) community, independently. While in fairness-aware ML, the focus is usually on ensuring that the predictions made by a learned model are fair, in reality the fairness should be guaranteed for the decisions made using such predictions. Existing methods in fairness-aware optimization resolve this issue, however they are often deterministic and fall short in exploiting the knowledge which is available in data. Golnoosh Farnadi’s research focuses on the complementary strengths of fairness methods in ML and OR to address these shortcomings in a fair data-driven decision making system.