Article Source

• Fairness and Bias in Algorithmic Decision-Making

Fairness and Bias in Algorithmic Decision-Making

Abstract

Public debates about classification by algorithms has created tension around what it means to be fair to different groups. As part of Northwestern Engineering’s Dean’s Seminar Series on May 13, Cornell University’s Jon Kleinberg discussed key fairness conditions at the heart of these debates, and recent work on the interactions between these conditions. He also explored how the complexity of a classification rule interacts with its fairness properties, showing how natural ways of approximating a classifier via a simpler rule can act in conflict with fairness goals.

Analyzing Bias in Machine-Learning Algorithms

Abstract

Recent discussion in the public sphere has explored some of the way in which prediction algorithms trained on data might exhibit bias in their decision-making. This discussion, drawing on input from a wide range of communities, has involved a number of crucial trade-offs that can be formulated in precise terms. We will survey some of these trade-offs, including tensions between the simplicity of a classification rule and its equity guarantees, and tensions between competing definitions of what it means for a prediction algorithm to be fair to different groups.