Authors:
Sonjoy Ranjon Das, Rejwan Bin Sulaiman, Usman Butt

Addresses:
1,2Department of Computer Science and Technology, Northumbria University, London, United Kingdom. 3Faculty of Engineering and Information Technology, The British University in Dubai, Dubai, United Arab Emirates. sonjoy.das@northumbria.ac.uk1, rejwan.sulaiman@northumbria.ac.uk2, usman.butt@buid.ac.ae3

Abstract:

The issue of credit card fraud poses a significant concern for users of online transactions, necessitating the implementation of effective fraud detection mechanisms. Fraud detection is often done using machine learning algorithms. Practitioners can compare and analyse algorithms to get the best one for their credit card fraud detection scenario. This article describes a detailed study to find the best credit card fraud forecasting model. The study tests cutting-edge supervised machine learning methods on two datasets. Using eight algorithms improves credit card fraud detection accuracy and efficacy. Logistic Regression, Decision Trees, Random Forests, Multilayer Perceptions, Naive Bayes, XGBoost, KNN, and SVM are examples (SVM). Additionally, Principal Component Analysis (PCA) is used to reduce dimensionality and improve algorithm performance during experimentation. XGBoost has the maximum accuracy of 99.96 percent for the first dataset, while Random Forest has 99.92 percent for the second. Cross-validation with Logistic Regression, Decision Trees, Random Forests, and XGBoost proves Random Forests are better at credit card fraud detection. Random Forests excel at undersampling and oversampling. Thus, this paper proposes XGBoost and Random Forests as the most reliable credit card fraud detection algorithms. 

Keywords: Comparative Analysis; Machine Learning Algorithms; Random Forests; Multilayer Perceptions; Naive Bayes; Credit Card Fraud Detection; Fraud Detection Mechanisms; Principal Component Analysis; Logistic Regression.

Received on: 09/05/2023, Revised on: 05/09/2023, Accepted on: 22/10/2023, Published on: 20/12/2023

FMDB Transactions on Sustainable Computing Systems, 2023 Vol. 1 No. 4, Pages: 225-244

• Views : 195
• Downloads : 16

Download PDF