Authors:
Rejwan Bin Sulaiman, Mohammad Aljaidi, Amjad A. Alsuwaylimi, Usman Butt, Md. Simul HasanTalukder, Syeda Sadia Alam, Maruf Farhan, Sanjoy Ranjon Das, Md Wahidul Alam

Addresses:
Department of Computer Science, Northumbria University, Tyne, England, United Kingdom. Department of Computer Science, Zarqa University, Zarqa, Jordan. Department of Computer Science, Northern Border University, Arar, Saudi Arabia. Department of Computer Science, British University, Dubai, United Arab Emirates. Department of Computer Science, Bangladesh Atomic Energy Regulatory Authority (BAERA), Dhaka, Bangladesh. Department of Computer Science, Metropolitan University, Sylhet, Bangladesh. Department of Computer Science, Northumbria University, Tyne, England, United Kingdom. Department of Computer Science, Shipley College, Shipley, United Kingdom. Department of Computer Science, University of York, Heslington, York, England, United Kingdom. rejwan.sulaiman@northumbria.ac.uk, mjaidi@zu.edu.jo, Amjad.alsuwaylimi@nbu.edu.sa, usman.butt@buid.ac.ae, simulhasantalukder@gmail.com, Syeda.alam.juti@gmail.com, Marufrigan9@gmail.com, Sonjoyict@gmail.com, alamw69@gmail.com

Abstract:

Nowadays, credit card transactions are exponentially increasing as a form of online payment. That creates technical pressure on the financial institution to incur losses due to credit card fraud. It is no wonder that credit card fraud is making people feel insecure and unsafe about using the services provided by banks. Data mining reasons on offline and online transactions can cause fraud detection. Number one is the changes in the behaviour of the frauds that are changing, and number two is the fraudulent dataset, which is asymmetric. In addition, the variables and techniques used by the researcher can impact fraud detection activities for credit cards. Therefore, the paper intends to investigate the suitability of the k-nearest-neighbour, decision tree, support vector machine, logistic regression, and Catboost. The data set has a total of 284807 transactions coming from the European credit card holder. Evaluation of the performance can be measured through the specificity, accuracy, sensitivity, precision, and lastly, the recall rate. After completing the comprehensive cross-validation, it was discovered that the catboost’s accuracy was extraordinary, which amounted to 93.39%, leaving the other classification matrix far behind.

Keywords: Enhancing Security; Digital Payments; Machine Learning Models; Credit Card Fraud Detection; K-nearest-neighbour (KNN); Decision Tree (DT); Support Vector Machine (SVM); Logistic Regression (LR).

Received on: 05/12/2023, Revised on: 09/02/2024, Accepted on: 01/04/2024, Published on: 09/06/2024

DOI: 10.69888/FTSCL.2024.000182

FMDB Transactions on Sustainable Computer Letters, 2024 Vol. 2 No. 2, Pages: 63-84

• Views : 144
• Downloads : 11

Download PDF