Credit Card Fraud Prediction Based on the Improved Data Balancing Technique and the Gradient Boosting Algorithm

DOI

10.2991/978-94-6463-368-9_74How to use a DOI?

Keywords

Credit Card Fraud; Imbalanced Data; Gradient Boosting; Stacking; Financial Transaction Security; Classification

Abstract

This paper aims to build a credit card transaction fraud classification model by combining improved data balancing techniques and gradient boosting algorithms. After data cleaning and preprocessing, we applied random oversampling, SMOTE oversampling, random undersampling, and Tomek Links undersampling methods to deal with the highly imbalanced dataset. Afterwards, we established classification models using LightGBM, XGBoost and CatBoost algorithms for comparative experiments. Finally, we selected the best performing gradient boosting model under each data balancing method as the first layer models of the Stacking algorithm, and the classification tree model as the second layer model. Its accuracy and F1-score on the testing set reached 0.98.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ying Jin
AU  - Yanming Chen
PY  - 2024
DA  - 2024/02/14
TI  - Credit Card Fraud Prediction Based on the Improved Data Balancing Technique and the Gradient Boosting Algorithm
BT  - Proceedings of the 2023 5th International Conference on Economic Management and Cultural Industry (ICEMCI 2023)
PB  - Atlantis Press
SP  - 621
EP  - 629
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-368-9_74
DO  - 10.2991/978-94-6463-368-9_74
ID  - Jin2024
ER  -