DeepAI AI Chat
Log In Sign Up

Learning to be Fair: A Consequentialist Approach to Equitable Decision-Making

by   Alex Chohlas-Wood, et al.

In the dominant paradigm for designing equitable machine learning systems, one works to ensure that model predictions satisfy various fairness criteria, such as parity in error rates across race, gender, and other legally protected traits. That approach, however, typically divorces predictions from the downstream outcomes they ultimately affect, and, as a result, can induce unexpected harms. Here we present an alternative framework for fairness that directly anticipates the consequences of actions. Stakeholders first specify preferences over the possible outcomes of an algorithmically informed decision-making process. For example, lenders may prefer extending credit to those most likely to repay a loan, while also preferring similar lending rates across neighborhoods. One then searches the space of decision policies to maximize the specified utility. We develop and describe a method for efficiently learning these optimal policies from data for a large family of expressive utility functions, facilitating a more holistic approach to equitable decision-making.


page 1

page 2

page 3

page 4


Enforcing Group Fairness in Algorithmic Decision Making: Utility Maximization Under Sufficiency

Binary decision making classifiers are not fair by default. Fairness req...

SCALES: From Fairness Principles to Constrained Decision-Making

This paper proposes SCALES, a general framework that translates well-est...

Causal Conceptions of Fairness and their Consequences

Recent work highlights the role of causality in designing equitable deci...

iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making

People are rated and ranked, towards algorithmic decision making in an i...

Comparing Fairness Criteria Based on Social Outcome

Fairness in algorithmic decision-making processes is attracting increasi...

α-Discounting Multi-Criteria Decision Making (α-D MCDM)

In this book we introduce a new procedure called α-Discounting Method fo...

From Predictions to Decisions: Using Lookahead Regularization

Machine learning is a powerful tool for predicting human-related outcome...