DeepAI AI Chat
Log In Sign Up

Modeling Epistemological Principles for Bias Mitigation in AI Systems: An Illustration in Hiring Decisions

by   Marisa Vasconcelos, et al.

Artificial Intelligence (AI) has been used extensively in automatic decision making in a broad variety of scenarios, ranging from credit ratings for loans to recommendations of movies. Traditional design guidelines for AI models focus essentially on accuracy maximization, but recent work has shown that economically irrational and socially unacceptable scenarios of discrimination and unfairness are likely to arise unless these issues are explicitly addressed. This undesirable behavior has several possible sources, such as biased datasets used for training that may not be detected in black-box models. After pointing out connections between such bias of AI and the problem of induction, we focus on Popper's contributions after Hume's, which offer a logical theory of preferences. An AI model can be preferred over others on purely rational grounds after one or more attempts at refutation based on accuracy and fairness. Inspired by such epistemological principles, this paper proposes a structured approach to mitigate discrimination and unfairness caused by bias in AI systems. In the proposed computational framework, models are selected and enhanced after attempts at refutation. To illustrate our discussion, we focus on hiring decision scenarios where an AI system filters in which job applicants should go to the interview phase.


page 1

page 2

page 3

page 4


Bias and Discrimination in AI: a cross-disciplinary perspective

With the widespread and pervasive use of Artificial Intelligence (AI) fo...

Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies

The significant advancements in applying Artificial Intelligence (AI) to...

Speciesist bias in AI – How AI applications perpetuate discrimination and unfair outcomes against animals

Massive efforts are made to reduce biases in both data and algorithms in...

Challenges and Solutions in AI for All

Artificial Intelligence (AI)'s pervasive presence and variety necessitat...

Fairness Assessment for Artificial Intelligence in Financial Industry

Artificial Intelligence (AI) is an important driving force for the devel...

Testing Framework for Black-box AI Models

With widespread adoption of AI models for important decision making, ens...

Fairness Evaluation in Deepfake Detection Models using Metamorphic Testing

Fairness of deepfake detectors in the presence of anomalies are not well...