Feature selection strategies: a comparative analysis of SHAP-value and importance-based methods

Feature selection strategies: a comparative analysis of SHAP-value and importance-based methods

Abstract In the context of high-dimensional credit card fraud data, researchers and practitioners commonly utilize feature selection techniques to enhance the performance of fraud detection models. This study presents a comparison in model performance using the most important features selected by SH...

Full description

Bibliographic Details
Main Authors: Huanjing Wang, Qianxin Liang, John T. Hancock, Taghi M. Khoshgoftaar
Format: Article
Language:English
Published: SpringerOpen 2024-03-01
Series:Journal of Big Data
Subjects:
Feature selection
Class imbalance
Credit card fraud
SHAP
Feature importance
Online Access:https://doi.org/10.1186/s40537-024-00905-w

Internet

https://doi.org/10.1186/s40537-024-00905-w

Similar Items