Credit Card Detection by Applying Interpretable Tree-Based Machine Learning Models

DOI

10.2991/978-94-6463-210-1_34How to use a DOI?

Keywords

Machine learning; credit card fraud detection; decision tree classifier; random forest classifier; extra tree classifier

Abstract

Credit card security issues have emerged in recent decades as the usage of credit cards for payment has increased. As a result, more and more credit card fraud instances have occurred, drawing significant attention from financial and academic circles. This work intends to employ three interpretable tree-based models, namely decision tree classifier, random forest classifier, and extra tree classifier to detect credit card fraud instances and employ Area Under Curve, Accuracy, Positive Predicted Value, recall, and F1 score as indicators to evaluate their performance while dealing with the challenges of extensive sample data and severely imbalanced data in credit card fraud detection. In addition, the feature importance based on these three models is also presented to observe the degree of correlation between each input feature variable and the predicted label during the model training process. The experimental results indicate that the extra tree classifier, this ensemble model performs better in this detection, which can assist credit card users and institutions in completing credit card detection in organizing the occurrence of fraud events as much as feasible.

Copyright

© 2023 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  - Shizhao Xiong
PY  - 2023
DA  - 2023/07/25
TI  - Credit Card Detection by Applying Interpretable Tree-Based Machine Learning Models
BT  - 2023 4th International Conference on E-Commerce and Internet Technology (ECIT 2023)
PB  - Atlantis Press
SP  - 266
EP  - 272
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-210-1_34
DO  - 10.2991/978-94-6463-210-1_34
ID  - Xiong2023
ER  -