A Novel text2IMG Mechanism of Credit Card Fraud Detection: A Deep Learning Approach

Abdullah Alharbi,Majid Alshammari,Hafiz Tayyab Rauf,Ofonime Dominic Okon,Amerah Alabrah,Hashem Alyami,Talha Meraj

doi:10.3390/electronics11050756

Abstract

Online sales and purchases are increasing daily, and they generally involve credit card transactions. This not only provides convenience to the end-user but also increases the frequency of online credit card fraud. In the recent years, in some countries, this fraud increase has led to an exponential increase in credit card fraud detection, which has become increasingly important to address this security issue. Recent studies have proposed machine learning (ML)-based solutions for detecting fraudulent credit card transactions, but their detection scores still need improvement due to the imbalance of classes in any given dataset. Few approaches have achieved exceptional results on different datasets. In this study, the Kaggle dataset was used to develop a deep learning (DL)-based approach to solve the text data problem. A novel text2IMG conversion technique is proposed that generates small images. The images are fed into a CNN architecture with class weights using the inverse frequency method to resolve the class imbalance issue. DL and ML approaches were applied to verify the robustness and validity of the proposed system. An accuracy of 99.87% was achieved by Coarse-KNN using deep features of the proposed CNN.

Highlights

Credit cards are used extensively for online shopping, which has substantially increased due to globalization
If we examine the number of class instances in the dataset, we can see that a significant class imbalance issue is created, which is addressed using the inverse frequency method, in which class weights based on the class frequency are assigned for pixel classification of the proposed Convolutional Neural Network (CNN)
These results are from tests on 30% of the data, which might not be highly reliable if big data are input

Summary

Introduction

Credit cards are used extensively for online shopping, which has substantially increased due to globalization. The higher number of credit card transactions (CCTs) has resulted in an increased incidence of fraud [1], necessitating the development of novel fraud detection methods. The process of stealing someone’s identity and performing fraudulent transactions by pretending to be the card owner is called credit card crime (CCC), and credit card fraud detection (CCFD) methods are applied to detect such fraudulent transactions. There are two types of fraudulent transactions, i.e., offline fraud and online fraud. Offline fraud is conducted by physically stealing the card and physically using it afterward, whereas online fraud is conducted by stealing the victim’s personal information, such as the card holder’s name, card number, and pin code [3]. Regardless of the fraud identification model (FIM) used, fraudulent transactions should be identified first [3]

Methods

Results

Conclusion