Paper Type

Short

Paper Number

PACIS2025-1073

Description

Imbalanced datasets are common in many real-world applications, where the number of instances in one class is significantly lower than the other. This can lead to poor performance of machine learning models, as they tend to favor the majority class. In this paper, we propose a novel approach to balance imbalanced datasets that consider both class imbalance and model fairness and cost. Our method utilizes a customized crowding distance measure to achieve a balance between classes while ensuring the model is fair to all groups

Comments

General

Share

COinS
 
Jul 6th, 12:00 AM

A Tailored NSGA-II Approach for Responsible Managerial ML Optimization on Imbalanced Data

Imbalanced datasets are common in many real-world applications, where the number of instances in one class is significantly lower than the other. This can lead to poor performance of machine learning models, as they tend to favor the majority class. In this paper, we propose a novel approach to balance imbalanced datasets that consider both class imbalance and model fairness and cost. Our method utilizes a customized crowding distance measure to achieve a balance between classes while ensuring the model is fair to all groups