Algorithmic Fairness: A Case Study in Banking

Details

Supervisors

Saerens, Marco

Faculty

Louvain School of Management

Degree label

Master [120] : ingénieur de gestion, à finalité spécialisée

Abstract

This thesis addresses the pivotal topic of algorithmic fairness in predictive modeling, particularly in the banking environment, using ING’s 'pi_nextinvest' model as a case study. We critically explore the concept, implications, and mitigation strategies of algorithmic bias, applying various fairness enhancement techniques in pre-processing, in-processing, and post-processing stages. The findings highlight a complex interplay between fairness and predictive performance, emphasizing that achieving algorithmic fairness is not a linear task but rather a delicate balance contingent on specific contexts and constraints.