Banca de QUALIFICAÇÃO: ELI JOSÉ BATISTA JÚNIOR

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : ELI JOSÉ BATISTA JÚNIOR
DATE: 17/12/2024
TIME: 15:30
LOCAL: Vídeo Conferência
TITLE:

Biases Mitigation in Machine Learning

KEY WORDS:

Machine Learning, Bias, Fairness, Metric, Mitigation

PAGES: 24
BIG AREA: Ciências Sociais Aplicadas
AREA: Economia
SUMMARY:

This work aims to conduct a literature review on bias mitigation in machine learning, addressing the challenge of balancing bias mitigation with improving model accuracy, focusing on the pursuit of fair ML models. We will begin by building a bridge between the usual econometric knowledge possessed by economists and other social scientists and the common tools used in machine learning. Next, we will move on to the definitions of bias and fairness, distinguishing one from the other. Once this is established, we will be prepared to analyze existing metrics, interpret them, and then evaluate the best ways to use them. Subsequently, we will relate and analyze the known and available mitigation techniques and tools on the market. Finally, aiming to produce practical knowledge, one or more problems will be selected to apply the concepts, techniques, and tools, in order to compare the results and discuss whether or not fair outcomes have been achieved

COMMITTEE MEMBERS:
Presidente - 1642911 - DANIEL OLIVEIRA CAJUEIRO
Externo ao Programa - 1997721 - HERBERT KIMURA - null