Credit Card Fraud Detection using Machine Learning Techniques

The COVID-19 pandemic has caused a huge decline in money usage, with everything turning online these days. It has contributed to an increase in contactless payments that was unimaginable before. A credit card is the most extensively used method of payment, and it is becoming increasingly digital as the number of daily electronic transactions increases, making it more vulnerable to fraud. Credit card firms have suffered losses because of widespread card fraud. The most common worry is the recognition of credit card fraud. As a result, organizations are looking toward advanced device understanding technologies since they can handle a lot of data and spot irregularities that humans would miss. The development of effective To stop these losses, fraud detection algorithms are essential. An increasing number of these algorithms rely on cutting-edge computer methods that can assist fraud investigators. However, the appearance of the full-proof Fraud Detection System demands the use of high performing algorithms that are both exact and sturdy enough to handle massive amounts of data. The algorithm is run using open-source software using R statistical programming. This project tries to provide options by studying several fraud detection systems and highlighting their strengths and limitations. © 2022 IEEE.

Class balancing framework for credit card fraud detection based on clustering and similarity-based selection (SBS).

Credit card fraud is a growing problem nowadays and it has escalated during COVID-19 due to the authorities in many countries requiring people to use cashless transactions. Every year, billions of Euros are lost due to credit card fraud transactions, therefore, fraud detection systems are essential for financial institutions. As the classes' distribution is not equally represented in the credit card dataset, the machine learning trains the model according to the majority class which leads to inaccurate fraud predictions. For that, in this research, we mainly focus on processing unbalanced data by using an under-sampling technique to get more accurate and better results with different machine learning algorithms. We propose a framework that is based on clustering the dataset using fuzzy C-means and selecting similar fraud and normal instances that have the same features, which guarantees the integrity between the data features.

Credit Card Fraud Detection: Challenges and Techniques

Credit card usage has risen dramatically as a result of rapid advancements in electronic commerce and the unexpected circumstance of COVID. With credit cards becoming the most popular payment method for both offline and online transactions, the number of cases of fraud associated with them is rapidly increasing. In case of online fraud, it is not necessary for the perpetrators to be present at the scene of crime. The fraudulent activities can be accomplished by them in the seclusion of their homes through a multitude of methods for disguising their identities. VPNs are one way to obscure one's identity, as is routing communication through any Tor network for the victim, making it difficult to track back the culprit. © 2022 IEEE.

Credit Card Fraud Detection Web Application using Streamlit and Machine Learning

Credit Card Fraud is one of the major threads in the financial industry. Due to the covid-19 pandemic and the advance in technologies, the number of users is increasing, with the increased use of credit cards. Due to more use of credit cards, Fraud cases also increase day by day. The research community striving hard to explore myriad credit card fraud detection techniques, but changes in technology and the varying nature of credit card fraud make it difficult to develop an effective technique for the detection of credit card fraud. This research work used a real-world credit card dataset. To detect the fraud transaction within this dataset three machine learning algorithms are used (i.e. Random Forest, Logistic regression, and AdaBoost) and compared the machine learning algorithms based on their Accuracy and Mathews Correlation Coefficient (MCC) Score. In these three algorithms, the Random Forest Algorithm achieved the best Accuracy and MCC score. The Streamlit framework is used to create the machine learning web application. © 2022 IEEE.

Credit Card Fraud Detection by Improved SVDD

The COVID-19 pandemic has brought dramatic changes in human beings' habits. One of these major changes is the increase use of credit card. Online shopping has become necessary to satisfy customers' needs during the pandemic. However, this kind of shopping opened a new way to hack information. Several research studies have focused on automatic and real-time online credit card fraud detection. In this context, machine learning (ML) techniques have played a considerable part in these studies, thanks to their characteristics that provide a model capable of detecting fraudulent transactions. This article aims to design a hybrid model for credit card fraud detection. Our hybrid solution combines the Support Vector Data Description (SVDD) and the Particle Swarm Optimization (PSO). For instance, SVDD is known by a random choice of two parameters, c and σ, which contribute to its efficiency. The proposed model uses the PSO algorithm, known by its speed, to find an optimal solution to optimize these two parameters to obtain better accuracy. Simulation results of real datasets indicate SVDD-PSO's performance compared to other machine learning techniques. © 2022 Newswood Limited. All rights reserved.

Financial Fraud Detection Approach Based on Firefly Optimization Algorithm and Support Vector Machine

The usage of credit cards is increasing daily for online transactions to buy and sell goods, and this has also increased the frequency of online credit card fraud. Credit card fraud has become a serious issue for financial institutions over the last decades. Recent research has developed a machine learning (ML)-based credit card fraud transaction system, but due to the high dimensionality of the feature vector and the issue of class imbalance in any credit card dataset, there is a need to adopt optimization techniques. In this paper, a new methodology has been proposed for detecting credit card fraud (financial fraud) that is a hybridization of the firefly bio-inspired optimization algorithm and a support vector machine (called FFSVM), which comprises two sequential levels. In the first level, the firefly algorithm (FFA) and the CfsSubsetEval feature section method have been applied to optimize the subset of features, while in the second level, the support vector machine classifier has been used to build the training model for the detection of credit card fraud cases. Furthermore, a comparative study has been performed between the proposed approach and the existing techniques. The proposed approach has achieved an accuracy of 85.65% and successfully classified 591 transactions, which is far better than the existing techniques. The proposed approach has enhanced classification accuracy, reduced incorrect classification of credit card transactions, and reduced misclassification costs. The evaluation results show that the proposed FFSVM method outperforms other nonoptimization machine learning techniques.

A Novel Approach in Credit Card Fraud Detection System Using Machine Learning Techniques

With the rapid expansion of daily life, the use of credit cards for online purchases is steadily increasing and credit card fraud is on the rise. Nowadays, in the social distancing environment, due to covid-1, 9online shopping has become important. Credit card credentials are used to make online payments, and then deduct money which does not involve any contact and makes people's life difficult. Because of this, finding the most effective method of detecting scams in online systems is essential. To prevent customers from being charged for goods they have not purchased, credit card companies must be able to identify fraudulent credit card transactions. Therefore, there are several theories either completed or proceeding to detect these kinds of frauds. This study is an approach to identify non-legitimate transactions using semi-supervised machine learning models by explaining how to deal with imbalanced datasets, using a wide variety of models to better understand which ones work better. © 2021 IEEE.