An Innovative Approach to Detecting Credit Card Fraud Through Decision-Making Algorithms for Trees and Random Forests
DOI:
https://doi.org/10.62643/Abstract
New methods of doing business emerged in the financial sector with the expansion of technology. One of them is the credit card system. However, many issues with credit card frauds have arisen as a result of several vulnerabilities in this system. This is causing a tremendous loss for the business and for consumers who pay with credit cards. When it comes to privacy concerns, there is a lack of investigation lessons on looking at real credit card numbers. An effort to detect credit card fraud using algorithms that use machine learning approaches is presented in the article. Two algorithms are used for this purpose: one for credit card fraud detection using Decision Tree and the other for random forest fraud detection. It is possible to determine the model's efficiency by sampling from a set of publicly available data. The next step is to look at a real-life credit card data set that a bank has. In addition, the data samples are enhanced with additional noise to further verify the systems' robustness. An important part of the approaches presented in the study is the first one, which builds a tree based on the user's actions and uses it to detect frauds. The second approach involves building an activity-based forest and then trying to identify the suspect using this forest. When it comes to detecting credit card fraud, the research results show that the popular alternative method achieves respectable levels of accuracy.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.