Unbalanced Credit Card Fraud Detection Data: A Machine Learning-Oriented Comparative Study of Balancing Techniques

With the continuous expansion of the banks' credit card businesses, credit card fraud has become a serious threat to banking financial institutions. So, the automatic and real-time credit card fraud detection is the meaningful research work. Because machine learning has the characteristics of non-linearity, automation, and intelligence, so that credit card fraud detection can improve the detection efficiency and accuracy. In view of this, this paper proposes a credit card fraud detection model based on heterogeneous ensemble, namely CUS-RF (cluster-based under-sampling boosting and random forest), based on clustering under-sampling and random forest algorithm. CUS-RF-based credit card fraud detection model has the following advantages. Firstly, the CUS-RF model can better overcome the issue of data imbalance. Secondly, based on the idea of heterogeneous ensemble learning, the clustering under-sampling method and random forest model are fused to achieve a better performance for credit card fraud detection. Finally, through the verification of real credit card fraud dataset, the CUS-RF model proposed in this paper has achieved better performance in credit card fraud detection compared with the benchmark model.

With increased internet usage, online transactions have been on the rise. One of the most prevalent problems faced is credit cards frauds. While web applications and mailing services are heavily spammed, the upsurge of handheld mobile devices has led to an outburst of heavy mobile credit card spamming. The matter is more severe in mobile devices due to lesser sophisticated filtering mechanisms in built in mobile operating systems. Recent advancements in electronic commerce and communication systems have significantly increased the use of credit cards for both online and regular transactions. However, there has been a steady rise in fraudulent credit card transactions, costing financial companies huge losses every year. The development of effective fraud detection algorithms is vital in minimizing these losses, but it is challenging because most credit card datasets are highly imbalanced. This work proposes a supervised machine learning algorithm to be trained to detect credit card frauds based on the Bayes Net with penalty based regularization. It is shown that the proposed approach attains higher classification accuracy compared to existing work. Keywords— Credit Card Fraud Detection, Machine Learning, Feature Selection, Imbalanced Datasets, Probabilistic Classifier, Classification Accuracy

The increase of Credit Card (CC) fraud in recent years requires the development of fraud detection systems that are both efficient and robust. This paper explored the utilization of machine learning models, with a particular emphasis on ensemble methods, to advance the detection of CC fraud. We present an ensemble model that incorporates different classifiers to address the dataset imbalance issue that is present in most CC datasets. We employed synthetic over-sampling and under-sampling techniques in certain machine learning algorithms to tackle the same issue. To address the issue of under sampling, we implemented ensemble random sampling, which was subsequently followed by Two-Stage Thresholding (TST) to eliminate outliers. The well-known Synthetic Minority Over-sampling Technique (SMOTE) was used for over-sampling. Data was utilized to train the model and subsequently generate predictions by utilizing testing data following the pre-processing of the dataset. The proposed ensemble model outperformed conventional methods in addressing the challenges associated with CC fraud detection, as demonstrated by a comparative analysis. Our findings suggest that ensemble approaches are effective at fighting fraud, paving the way for more adaptive and resilient fraud detection systems.

Financial fraud is a serious threat that is expanding effects on the financial sector. The use of credit cards is growing as digitization and internet transactions advance daily. The most common issues in today's culture are credit card scams. This kind of fraud typically happens when someone uses someone else's credit card details. Credit card fraud detection uses transaction data attributes to identify credit card fraud, which can save significant financial losses and affluence the burden on the police. The detection of credit card fraud has three difficulties: uneven data, an abundance of unseen variables, and the selection of an appropriate threshold to improve the models' reliability. This study employs a modified Logistic Regression (LR) model to detect credit card fraud in order to get over the preceding difficulties. The dataset sampling strategy, variable choice, and detection methods employed all have a significant impact on the effectiveness of fraud detection in credit card transactions. The effectiveness of naive bayes, k-nearest neighbour, and logistic regression on highly skewed credit card fraud data is examined in this research. The accuracy of the logistic regression technique will be closer to 0.98%; with this accuracy, frauds may be easily detected. The fact that LR receives the highest classifier score illustrates how well LR predicts credit card theft.

Abstract: With the increasing reliance on online transactions across sectors such as banking, telecommunications, insurance, and e-commerce, credit card fraud has emerged as a critical concern. The widespread use of electronic payment systems, particularly credit and debit cards, has made fraudulent activities more prevalent and sophisticated. Credit card fraud detection presents a complex classification problem that can be effectively addressed using machine learning (ML) techniques. This study explores the capabilities of ML algorithms in detecting fraudulent credit card transactions by examining both the challenges and opportunities in this domain. Adopting a mixed-method approach that combines a comprehensive literature review with experimental evaluation, the study investigates how past transaction data distinguishing between legitimate and fraudulent activities can be modeled to classify new transactions accurately. The research advocates for a progressive transition towards hybrid models that integrate machine learning with deep learning techniques to enhance the robustness and adaptability of fraud detection systems.

Online credit card transactions have witnessed a steady year-to-year growth, making fraud detection an increasingly critical challenge. Credit card fraud detection is particularly difficult due to the extreme class imbalance between fraudulent and non-fraudulent transactions. Imbalanced data, where one class heavily dominates the other, must be addressed before effective fraud detection can be achieved. Traditional oversampling techniques such as the Synthetic Minority Over-sampling Technique (SMOTE) and its variants often generate synthetic samples without considering the importance of ranking performance in the minority class distribution, leading to suboptimal classification performance. To address this, an adaptive Weight and rank-based Minority (WRM-SMOTE) oversampling method is proposed that prioritizes the performance and its relative ranking. To the best of our knowledge, WRM-SMOTE is among the first method to combine performance-based weighting and ranking across multiple SMOTE variants for adaptive oversampling. This method transforms imbalanced datasets into balanced ones through adaptive synthetic sample generation. The process begins by computing a weight based on two componentsabsolute performance and relative ranking. This is done to provide a distinction between two variants with extremely similar performance when one outperforms the other. Our experimental results on real-world credit card fraud datasets and eleven other benchmark datasets demonstrate that WRM-SMOTE significantly improves fraud detection performance, achieving higher precision and recall while maintaining a balanced false-positive rate compared to traditional oversampling methods. The proposed method effectively enhances classification accuracy by generating synthetic samples in high-impact regions thereby improving the robustness of fraud detection models.

The rapid growth of e-commerce and online banking has resulted in a substantial rise in credit card fraud incidents. Consequently, machine learning and advanced deep learning techniques have emerged as critical solutions. This study integrates the findings of a few researchers, examining diverse methodologies, including Naïve Bayes, K-Nearest Neighbor (KNN), Logistic Regression, CNN, RNN, and ensemble learning. A comparative performance analysis, emphasizing the challenges posed by imbalanced datasets, demonstrates the superior performance of hybrid models, in enhancing the accuracy of detecting the fraudulent in credit card transactions.

The explosive expansion of E-Commerce has led to a corresponding surge in credit card fraud as more people use their cards to make transactions online. Credit card fraud is on the rise as credit cards become the preferred method of payment for both online and in-store purchases. In practice, fraudulent and legitimate transactions coexist, and basic pattern-matching approaches are typically insufficient to identify fraud effectively. While Artificial Neural Networks (ANNs) offer several advantages, it's important to note that they require careful tuning, validation, and ongoing monitoring to ensure optimal performance. Additionally, the interpretability of ANNs can be a challenge, and efforts are being made to enhance model interpretability in the context of fraud detection. Identifying fraudulent transactions while avoiding false positives is the main objective of a credit card fraud detection system that uses ANNs effectively and correctly. Therefore, for credit card issues to reduce their loss, it is crucial that they implement reliable fraud detection systems. Various forms of credit card fraud may now be detected using cutting-edge methods based on Artificial Intelligence (AI), Data mining, Fuzzy logic, Machine learning (ML), sequence alignments, Genetics Programming, etc. An effective system for detecting credit card fraud requires a thorough grasp of all these methods. Using a set of predetermined criteria, this study examines the various neural network techniques currently in use for credit card fraud detection and provides an overall rating for each. The result shows 98% accuracy and 96% recall for the credit card fraud detection system.

Use of credit card is very common these days. And the number of frauds related to credit cards are also increasing. With the increase in the usage of internet, many organizations have shifted their work from offline to online. Same is the case with financial department. On one side, this thing has increased the ease of people but on the other hand, number of frauds have been tremendously increased. On one side, people are doing shopping without cash, paying bills without standing in long queues, doing booking online and on the other side fake accounts, scamming, credit card frauds have been increased resulting in huge amount of loss to financial system every year. Fraud is a criminal activity done by un authorized person. Credit card frauds are very common these days. There are many types of credit card frauds. Sometime they do fake calls or messages and sometimes they steal customer’s online information. Many techniques using machine learning models have been implemented in order to stop these types of frauds. But fraudsters are sometimes by pass theses traditional protective systems and make successful transaction. Traditional machine learning models are not capable enough to detect frauds using sequence of data. For this purpose, neural networks are recently used. In this paper, six machine learning algorithms are applied. Among them Random Forest and Extra trees classifier are best. And in case of neural networks, long short-term memory LSTM is best. Obtained results outperform the existed work that have been previously done in this field.

In today's socio-economic scenario, people rely heavily on credit cards.Moreover, credit cards are a requisite financial tool that enables its holders to make assets.It is true that credit cards, as a new method of payment, have become socially amenable to the masses.But nowadays, improvements in technology lead to growth in illegal activities.During credit card transactions many fraudsters can breach security and make fraudulent transactions to withdraw or transfer funds from one's account or e-wallets.The relevant literature presents many machine learning-based approaches for credit card detection, such as Logistic Regression, Decision Tree, CatBoost, Random Forest, Support Vector Machine, KNN, RNN, and CNN.The main focus has been to apply the recent development of deep learning algorithms for this purpose.Comparative analysis of both machine learning and deep learning algorithms was performed to find efficient outcomes.A machine learning algorithm was first applied to the dataset, which improved the accuracy of detection of the fraud to some extent.The proposed approaches can be implemented effectively for the real-world detection of credit card fraud.

Hemophilia 'A' (HA) is a genetic blood disorder characterized by a deficiency of Factor VIII (FVIII), with treatment often triggering the development of neutralizing antibodies (inhibitors) to FVIII. Predicting the development of these inhibitors is crucial for clinical applications but presents significant computational challenges due to data imbalance, skewed data, and inadequate data sanitization. This study aimed to develop a machine-learning/AI approach to find biomarkers and predict the development of inhibitors to Factor VIII in patients with Hemophilia 'A,' addressing the challenges associated with data imbalance and enhancing prediction accuracy. The data were sanitized and encoded for prediction, and the Random Over-sampling (ROS) technique was employed to resolve data imbalance in the CHAMP dataset. Several machine- learning classification models, including Random Forest, XG Boost, Cat Boost, Logistic Regression, Gradient Boosting, and Light GBM, were utilized. Hyperparameters were tuned using GridSearchCV optimization with a stratified k-fold approach. The performance of the models was evaluated based on accuracy, precision, recall, and F1 scores. The Random Forest model was further analyzed using an explainable AI (XAI) tool known as SHAP (SHapley Additive exPlanations) to identify the variables influencing model performance. The Random Forest model outperformed other classifiers, achieving a mean accuracy of 97.37%, along with closely aligned precision, recall, and F1 scores. The XAI tool SHAP facilitated the ranking of variables Clinical Severity, Variant Type, Exon, HGVS cDNA, hg19 Coordinates, and others according to their impact on the model's predictions. Additionally, the study identified biomarkers associated with FVIII inhibition. This study presents a breakthrough in the early prediction of inhibitor development in Hemophilia 'A' patients, paving the way for personalized and effective treatment programs. The integration of the preprocessing pipeline, Random Forest model, and SHAP analysis offers a novel solution for guiding treatment strategies for HA patients, which could significantly enhance the development of targeted and effective therapies.

Machine learning approaches are widely used to analyze and detect the increasingly serious problem of credit card fraud. However, typical credit card datasets present imbalanced classification situations because of severely skewed class distributions. Although researchers have proposed some strategies to deal with these imbalances, disadvantages remain. We propose an oversampling method based on variational automatic coding (VAE), combined with classic deep learning techniques, to solve this problem. The VAE method is used to generate a large amount of diverse cases from minority groups in an imbalanced dataset, which are then used to train the classification network. The proposed method is tested on an open credit card fraud dataset, which contains transactions conducted by European cardholders over two days in September 2013. Experimental results show that the VAE method performs better than synthetic minority oversampling techniques and traditional deep neural network methods. In addition, it outperforms recent oversampling methods based on generative adversarial network (GAN) models. After submitting the extended dataset to the baseline for training, the test of the VAE model performs well on indicators including precision, F-measure, accuracy and specificity. These experimental results suggest that the VAE-based oversampling method can be effectively applied to imbalanced classification problems.

With the continuous development of the economy, the widespread use of credit cards shows a growing trend. However, simultaneously, the risk of credit card fraud still exists and cannot be ignored. This article utilizes bank card data for model training, with a particular focus on addressing the high dimensionality and imbalance of data in credit card transactions. In terms of model construction, it introduces a reinforcement learning-based Long Short-Term Memory (LSTM) network. Additionally, to improve the classification and recognition performance of the model, ensemble learning algorithms and convolutional neural networks are employed for enhancement. The research results indicate that, compared to other methods, the approach proposed in this article demonstrates a higher level of performance in the AUC (Area Under the Curve) metric of 0.92, effectively preventing financial risks, and providing a more reliable solution for credit card fraud detection. In conclusion, after comparing numerous models, it is evident that LSTM is an effective algorithm choice, particularly suitable for credit card fraud detection tasks.

Credit Card Fraud, a fraudulent activity committed by stealing a credit card and using the same without knowledge or permission of the Card owner. Credit Card Fraud is usually committed by a criminal to purchase goods or services utilizing another account but the same card. Machine Learning algorithms can simplify the process of detection of fraudulent transaction. We show how various algorithms can be used to determine if the transaction is legitimate or not. We have split the dataset into test and train data. SMOTE technique has been on the train data for oversampling as the dataset being used is highly imbalanced. Machine Learning Classification techniques such as Gaussian Naive Bayes, Logistic Regression and Random Forest have been compared in this research. Based on the obtained performance measures, we can conclude that all three Machine Learning Models could be used for Fraudulent Transaction Detection.

Application of Credit Card Fraud Detection: Based on Bagging Ensemble Classifier