Bias Mitigation Methods for Binary Classification Decision-Making Systems: Survey and Recommendations

TL;DR

This paper surveys bias mitigation techniques in binary classification systems, analyzing their strengths and weaknesses, and offers recommendations for future research to enhance fairness in machine learning decision-making.

Contribution

It provides a comprehensive overview of existing bias mitigation methods, highlighting gaps and proposing directions for future development.

Findings

Most methods improve fairness but may reduce accuracy.

Trade-offs exist between bias reduction and model performance.

Recommendations aim to guide future bias mitigation research.

Abstract

Bias mitigation methods for binary classification decision-making systems have been widely researched due to the ever-growing importance of designing fair machine learning processes that are impartial and do not discriminate against individuals or groups based on protected personal characteristics. In this paper, we present a structured overview of the research landscape for bias mitigation methods, report on their benefits and limitations, and provide recommendations for the development of future bias mitigation methods for binary classification.