Comparative study on credit card fraud detection based on different support vector machines

Abstract

Credit card fraud is the new financial fraud crime accompanied by the gradual development of the economy which causes billions of dollars of losses every year. Credit card fraud case not only seriously violated the cardholder benefits and financial institutions, but also undermined the credit management order. However, fraudsters keep exploring new crime strategies constantly which exacerbates the crime rate of fraud. Thus, a predictive model for credit card fraud detection is essential to minimize its losses. By distinguishing between fraud and non-fraud, machine learning is one of the most efficient solutions for detecting fraud. Support vector machines have proven to be a novel algorithm with excellent performance. Nevertheless, the performance of SVM depends largely on the correct choice of model parameters (C and g), which could cause that the false positive was very high if the kernel function type and parameter cannot be selected properly. In this paper, based on the real transaction data of the credit card business, firstly, it will find the optimal kernel function suitable for the data set. Secondly, this paper will propose the method of optimizing the support vector machine parameters by the cuckoo search algorithm, genetic algorithm and particle swarm optimization algorithm. Last but not least, the Linear kernel function was found to be the best kernel function with an accuracy rate of 91.56%. Furthermore, the Radial basis function is used to optimize the kernel function, which can improve the accuracy from 42.86% to the highest accuracy rate of 98.05%. Compared with CS-SVM and GA-SVM, PSO-SVM has the best overall performance.

A systematic review of literature on credit card cyber fraud detection using machine and deep learning

“…Linear, radial, polynomial, and sigmoid are the four types of kernel functions, utilised in Li et al (2021) , this article uses SVM to detect credit card fraud. Using cuckoo search algorithm (CS) and genetic algorithm (GA) with particle swarm optimisation technique to optimise the SVM parameters (PSO).…”

A Study of Identification of Corporate Financial Fraud Using Neural Network Algorithms in an Information-based Environment

“…The decision tree algorithm [16] used the C5.0 decision tree model, and the depth of the model dendrogram was set to 22. In the SVM algorithm [17], the kernel function was a sigmoid function, and the penalty parameter was set to 2.…”

Syntax‐based metamorphic relation prediction via the bagging framework

“…Since the SVM classifier works well with small data sets, we take it as the main classifier. As a supervised learning algorithm for classification and regression problems (C. Li et al, 2021), SVM finds a hyper‐plane in the high‐dimensional space of the training data to obtain positive and negative classes. Based on the used data, parameters and applications, there are two types: linear SVM and nonlinear SVM.…”