An Experimental Study With Imbalanced Classification Approaches for Credit Card Fraud Detection

Abstract

Credit card fraud is a criminal offense. It causes severe damage to financial institutions and individuals. Therefore, the detection and prevention of fraudulent activities are critically important to financial institutions. Fraud detection and prevention are costly, time-consuming, and labor-intensive tasks. A number of significant research works have been dedicated to developing innovative solutions to detect different types of fraud. However, these solutions have been proved ineffective. According to Cifa, 33 305 cases of credit card identity fraud were reported between January and June in 2018. 1 Various weaknesses of existing solutions have been reported in the literature. Among them all, the imbalance classification is the most critical and well-known problem. Imbalance classification consists of having a small number of observations of the minority class compared with the majority in the data set. In this problem, the ratio fraud: legitimate is very small, which makes it extremely difficult for the classification algorithm to detect fraud cases. In this paper, we will conduct a rigorous experimental study with the solutions that tackle the imbalance classification problem. We explored these solutions along with the machine learning algorithms used for fraud detection. We identified their weaknesses and summarized the results that we obtained using a credit card fraud labeled dataset. According to this paper, imbalanced classification approaches are ineffective, especially when the data are highly imbalanced. This paper reveals that the existing approaches result in a large number of false alarms, which are costly to financial institutions. This may lead to inaccurate detection as well as increasing the occurrence of fraud cases.INDEX TERMS Fraud analysis and detection, fraud cybercrimes, imbalanced classification, secure society.

Minimizing the Overlapping Degree to Improve Class-Imbalanced Learning Under Sparse Feature Selection: Application to Fraud Detection

“…Based on a small stratified initial training set, Naïve Bayes iteratively teaches its base with the instances that the model is most uncertain about. Finally, Makki et al [39] confirmed an experimental study with different solutions to deal the imbalance classification issue. They explored these adopted techniques along with the machine learning algorithms applied to fraud detection and recognized their weaknesses.…”

Big Data: Analytical Solutions, Research Challenges and Trends

“…Credit card fraud considers one of the most common aspects of electronic fraud. Therefore, many approaches introduced to handle this problem and related fields, including illegal purchased for goods and services [107][108][109]. Another example compromises to healthcare services, that individuals and criminal networks whose commit fraud for nefarious reasons, personal gain, and obtaining medicines and medical supplies to gain private benefits illegally.…”

Evaluation of Deep Neural Networks for Reduction of Credit Card Fraud Alerts

“…When factoring in skewness, logistic regression, C5.0 classifier, Support Vector Machines and Artificial Neural Networks have proven [33] to perform better on imbalanced data than other techniques (Naïve Bayes, Bayesian Belief Network, Artificial Immune Systems, K Nearest Neighbors). Similar research [34] concluded that neural networks can better deal with imbalanced data than Support Vector Machines, Random Forest and decision trees.…”