Fraudulent Credit Card Transactions Research Articles

Quantum support vector machines for classification and regression on a trapped-ion quantum computer

Quantum machine learning is a rapidly growing field at the intersection of quantum computing and machine learning. In this work, we examine our quantum machine learning models, which are based on quantum support vector classification (QSVC) and quantum support vector regression (QSVR). We investigate these models using a quantum circuit simulator, both with and without noise, as well as the IonQ Harmony quantum processor. For the QSVC tasks, we use a dataset containing fraudulent credit card transactions and image datasets (the MNIST and the Fashion-MNIST datasets); for the QSVR tasks, we use a financial dataset and a materials dataset. For the classification tasks, the performance of our QSVC models using 4 qubits of the trapped-ion quantum computer was comparable to that obtained from noiseless quantum circuit simulations. The result is consistent with the analysis of our device noise simulations with varying qubit gate error rates. For the regression tasks, applying a low-rank approximation to the noisy quantum kernel, in combination with hyperparameter tuning in ε-SVR, improved the performance of the QSVR models on the near-term quantum device. The alignment, as measured by the Frobenius inner product between the noiseless and noisy quantum kernels, can serve as an indicator of the relative prediction performance on noisy quantum devices in comparison with their ideal counterparts. Our results suggest that the quantum kernel, as described by our shallow quantum circuit, can be effectively used for both QSVC and QSVR tasks, indicating its resistance to noise and its adaptability to various datasets.

Deep convolutional neural network based synthetic minority over sampling technique: a forfending model for fraudulent credit card transactions in financial institution

Fraudulent credit card transactions are committed by unauthorized individuals and organizations employing methods such as phishing and social engineering fraud tactics. Researchers propose several Machine Learning (ML) techniques to deter the challenges of credit card fraud. However, the ML approaches are endorsed with some challenges, which makes the detection of credit card fraud extremely difficult. This study proposes a Deep Convolutional Neural Network (DCNN) with Synthetic Minority Oversampling Techniques (SMOTE) as an ideal solution. Kaggle datasets with 284,807 records and 31 features were exploited. Implementation was performed on the Google Colab cloud-based platform, embedding a Jupyter notebook setting with Graphical Processing Units (GPUs). Two experiments were conducted; the first was probed to determine suitable models among baseline models: Logistic Regression (LR), Random Forest (RF), Isolation Forest, and a single Deep Learning (DL) model of Multiple Layer Perceptron (MLP). The baseline models yielded an overfitting accuracy score, with recall, specificity, precision, and F1-score all presenting 1.00% respectively. This outcome is not sufficient in establishing findings on imbalanced data distribution as it's biased. This led to the construction of a new ML model incorporating Light Gradient Boosting Machine (LGBM), with Artificial Neural Network (ANN) and the proposed DCNN+SMOTE for the second experimental phase alongside baseline models. Experimental results via simulation show the proposed DCNN+SMOTE yielded awesome superclass performance across the board, displaying 1.00% results respectively. Its Error Rate (ER) and Null Error Rate (NER) are 0.00% distinctly. Meanwhile, the False Positive Rate (FPR) yields a 0.001% result, lesser and better than the baseline models.

Credit Card Fraud Detection Challenges and Solutions: A Review

Credit card fraud has become an increasing problem due to the growing reliance on electronic payment systems and technological advances that have improved fraud techniques. Numerous financial institutions are looking for the best ways to leverage technological advancements to provide better services to their end users, and researchers used various protection methods to provide security and privacy for credit cards. Therefore, it is necessary to identify the challenges and the proposed solutions to address them. This review provides an overview of the most recent research on the detection of fraudulent credit card transactions to protect those transactions from tampering or improper use, which includes imbalance classes, concept drift, and verification latency problems using machine learning and deep learning. It also provides valuable information for academic and industrial researchers and opens new avenues for research aimed at developing robust fraud detection systems.

Fake Credit Transaction Detection Using Machine Learning

In today's digital age, detecting and preventing fraudulent credit card transactions is of paramount importance. As technology advances, criminal methods are also becoming more sophisticated. The use of machine learning in credit card fraud detection and mitigation has grown significantly. In this research study, a novel method for identifying fraudulent credit card transactions with machine learning algorithms is presented. The proposed system leverages past transaction data and various characteristics associated with each transaction, such as location, transaction amount, and time, to build a predictive model. These models are trained to recognize patterns that point to fraudulent activity using supervised learning methods like random forests and support vector machines. Several metrics, including accuracy, precision, recall, and F1 score, are used to assess the performance of the model. According to experimental data, the suggested method works better than conventional rule-based fraud detection systems and achieves high accuracy. The system can effectively detect fraudulent credit card transactions while minimizing false positives. Machine learning improves the security of credit card transactions by detecting fraud in real time. In summary, this study advances the field of credit card fraud detection by using machine learning algorithms to counteract the constantly changing tactics used by fraudsters.

Fraud Feature Boosting Mechanism and Spiral Oversampling Balancing Technique for Credit Card Fraud Detection

With the flourishing of the credit card business and Internet technology, the risk of fraudulent credit card transactions is ever-increasing due to the complex information involved in the credit card business. Since the high redundancy of feature information and imbalance of class distribution in transaction data, the performance of the existing machine learning-based models for detecting credit card fraudulent transactions still needs to be improved. Therefore, it is crucial to build fraud detection models for effective feature engineering and sampling techniques. This article proposes a credit card fraud detection model incorporating a fraud feature-boosting mechanism with a spiral oversampling balancing technique (SOBT). Specifically, we present a compound grouping elimination strategy to exclude highly redundant and correlated features from the credit card transaction dataset and improve the data quality. Furthermore, we design a multifactor synchronous embedding mechanism, which combines the performance evaluation metrics of the embedding model for each feature and improves the decision-making ability of each feature for the target domain. Moreover, we propose an SOBT to balance the ratio of legitimate to fraudulent transactions, which improves the ability of the fraud detection model to distinguish legitimate from fraudulent transactions. Extensive experimental results based on two real-world datasets demonstrate that our methods can facilitate efficient credit card fraud detection and achieve better performance than state-of-the-art methods.

CREDIT CARD FRAUD DETECTION USING MACHINE LEARNING ALGORITHMS

The Credit card frauds represent facile and amiable targets, particularly as the proliferation of e-commerce and various online platforms has led to a commensurate expansion in online payment modalities, thereby augmenting the susceptibility to online fraudulent activities. In response to the escalating rates of fraudulent incidents, researchers have undertaken the utilization of diverse machine learning methodologies to ascertain and scrutinize frauds within the realm of online transactions. The primary objective of this scholarly endeavor is to formulate and advance an innovative fraud detection modus operandi tailored for Streaming Transaction Data. The overarching goal is to meticulously scrutinize the historical transaction particulars of patrons and distill discernible behavioral patterns. This involves the clustering of cardholders into disparate cohorts predicated upon their transactional magnitudes. Subsequently, a sliding window strategy is employed to amalgamate transactions conducted by cardholders across distinct groups, facilitating the extraction of their respective behavioral patterns. Consecutively, diverse classifiers trained on these distinct groups, and the classifier exhibiting superior rating scores is earmarked as one of the preeminent methods for prognosticating fraudulent activities. This is succeeded by the implementation of a feedback mechanism aimed at mitigating the challenges posed by the phenomenon of concept drift. The empirical investigation detailed in this paper is grounded in the analysis of a European credit card fraud dataset. It is imperative for credit card companies to adeptly discern instances of fraudulent credit card transactions to preclude customers from incurring charges for items they did not legitimately acquire. The resolution to such quandaries lies in the realm of Data Science, a discipline whose significance, when coupled with Machine Learning, is of paramount importance. This undertaking endeavors to elucidate the construction of a model utilizing machine learning techniques for Credit Card Fraud Detection. The Credit Card Fraud Detection Problem entails the modeling of historical credit card transactions, incorporating data from those that transpired as fraudulent. Subsequently, this model is employed to ascertain the veracity of new transactions, distinguishing between fraudulent and non-fraudulent activities. The primary aim is the meticulous detection of 100% of fraudulent transactions, while concurrently minimizing instances of erroneous classifications of non-fraudulent transactions. Credit Card Fraud Detection serves as a quintessential exemplar of classification challenges. In the course of this endeavor, significant emphasis has been placed on the analysis and pre-processing of datasets. Furthermore, a diverse array of anomaly detection algorithms, including the Local Outlier Factor and Isolation Forest algorithm, have been deployed on Principal Component Analysis (PCA) transformed Credit Card Transaction data. KEYWORDS: Card-Not-Present frauds, Card-Present-Frauds, Concept Drift,,Credit card fraud, applications of machine learning, data science.

Credit Card Fraud Detection Using AI (Python)

Credit card fraud poses a formidable obstacle in the financial sector, resulting in considerable monetary damages for both individuals and institutions. The necessity for efficient fraud detection systems has become paramount due to the rising number of online transactions and the advancement of fraudulent methods. Machine learning methods have demonstrated potential in tackling this issue by utilizing past transaction data to detect fraudulent behavior. This study provides a thorough examination and evaluation of different machine learning techniques used in the detection of credit card fraud. The aim of this study is to assess and compare the efficacy of several machine learning algorithms in identifying fraudulent credit card transactions. The dataset utilized for experimentation is acquired from a prominent financial institution, including of both authentic and deceitful transactions. The dataset has been preprocessed to address missing values, outliers, and feature scaling. A variety of machine learning algorithms, such as “logistic regression, decision trees, random forests, support vector machines (SVM), and artificial neural networks (ANN),” are utilized and trained on the preprocessed information. The evaluation of each method is conducted using criteria like as “accuracy, precision, recall, and F1-score. In addition, several evaluation methods, such as k-fold cross-validation”, are used to assure the reliability of the findings. The empirical findings suggest that machine learning algorithms has the capability to accurately identify fraudulent credit card transactions. The algorithms demonstrate varying performance across different parameters, with certain algorithms displaying higher accuracy but worse precision or recall. The “Support Vector Machine (SVM)” algorithm gets the maximum accuracy rate of 98%, while the “Artificial Neural Network (ANN)” model displays the optimal balance between precision and recall..

IDENTIFYING FRAUD IN ONLINE TRANSACTIONS

Fraudulent credit card transactions must be when customers are charged for items that they did not purchase. Such problems can be tackled with Data Science and its importance, along with Machine Learning, cannot be overstated. This project intends to illustrate the modelling of a data set using machine learning with Identifying Fraud in Online Transactions. The Identifying Fraud in Online Transactions problem includes modelling past credit card transactions with the data of the ones that turned out to be a fraud. This model is then used to recognize whether a new transaction is fraudulent or not. Our objective here is to detect 99.99% of the fraudulent transactions while minimizing the incorrect fraud classifications. Identifying Fraud in Online Transactions is a typical sample of classification. In this process, we have focused on analyzing and pre-processing data sets by using a Random Forest Algorithm.

Comparative Analysis ofK-Nn, Naïve Bayes, and logistic regression for credit card fraud detection

Introduction:This paper highlights the outcome of the comparative study of “Various Machine learning algo-rithms namely K-NN, Naive Bayes, and Logistic Regression for Credit Card Fraud Detection” carried out based on a dataset taken from UCI.com in 2022-23 at Manav Rachna International Institute of Research and Studies.Problem: Credit card fraud is still rife today and the modes are increasingly varied. Quite often we hear of fraud cases that cause irreplaceable injury to banks and financial institutions which cannot be compensated in terms of costs. To avoid scams with various modes of credit cards, we must be able to identify and find out the modes often used by fraudsters. This scheme liberates such financial institutions and banks with complete and appropriate information using Machine Learning Techniques, not only about the modes that scammers or fraudsters often use but also ways to protect against such frauds.Objective: The present paper discusses the various machine learning models based on classification and re-gression, namely K-Nearest Neighbors, Naïve Bayes, and Logistic Regression, which are successfully able to achieve the classification accuracy of 80% using Logistic Regression with a Precision of 78%, Recall of 100%, and F1-Score of 88% for fraudulent credit card transactions. Methodology: The comparative analysis demonstrates that for Precision, Recall, and Accuracy parameters, the K-Nearest Neighbor is a better approach for detecting fraudulent transactions than the Logistic Regression and Naïve Bayes. Results:The accuracy is marginal high in Logistic Regression but the False Positive parameters are not able to identify the imbalanced data; therefore, they disguise the results and accuracy of Logistic Regression and K-Nearest Neighbor deems fit for such cases.Conclusion: This scheme depicts the automated fraud classification systems using machine learning techni-ques, namely K-Nearest Neighbor, Logistic Regression, and Naive Bayes, to produce a model that can distin-guish valid and invalid credit card transactions.Originality:Through this research, the most relevant features are used to go through the visualization of accu-racy with the confusion matrix, and accuracy calculations are obtained from the dataset used.Limitations:Deep learning techniques could have been used to fetch even better results.

Credit Card Fraud Detection: An Improved Strategy for High Recall Using KNN, LDA, and Linear Regression.

Efficiently and accurately identifying fraudulent credit card transactions has emerged as a significant global concern along with the growth of electronic commerce and the proliferation of Internet of Things (IoT) devices. In this regard, this paper proposes an improved algorithm for highly sensitive credit card fraud detection. Our approach leverages three machine learning models: K-nearest neighbor, linear discriminant analysis, and linear regression. Subsequently, we apply additional conditional statements, such as "IF" and "THEN", and operators, such as ">" and "<", to the results. The features extracted using this proposed strategy achieved a recall of 1.0000, 0.9701, 1.0000, and 0.9362 across the four tested fraud datasets. Consequently, this methodology outperforms other approaches employing single machine learning models in terms of recall.

Credit Card Fraud Detection Using Autoencoder &amp; Decoder ML

Abstract: In recent years credit card fraud has become one of the growing problems. It is vital that credit card companies can identify fraudulent credit card transactions, so that customers are not charged for the items that they did not purchase. The reputation of companies will heavily damage and endangered among the customers due to fraud in financial transactions The fraud detection techniques were increasing to improve accuracy to identify the fraudulent transactions. This project intends to build an unsupervised fraud detection method using autoencoder. An Autoencoder with four hidden layers which has been trained and tested with a dataset containing a European cardholder transaction that occurred in two days with 284,807 transactions from September 2013

Detection of fraud card and data breaches in credit card transactions

Data breaches and credit card fraud are now among the biggest problems affecting financial organizations and customers globally. The purpose of this study is to develop an effective fraud detection system that can detect fraudulent credit card transactions and prevent data breaches. The strategy proposed in this paper makes use of machine learning techniques like decision trees and logistic regression, to analyze large datasets of credit card transactions and identify suspicious patterns. The proposed system also includes a real-time monitoring mechanism that alerts the relevant authorities in case of any suspicious activity. The results of the experiments show that the suggested system achieves great accuracy and efficiency in detecting fraudulent transactions and data breaches. It can provide a powerful tool for financial institutions to prevent financial losses and maintain their customers' trust.

Implementation of Gradient Boosted Tree, Support Vector Machinery and Random Forest Algorithm to Detecting Financial Fraud in Credit Card Transactions

According to Google Trends data, machine learning-based credit card identification has grown over the last five years, at the very least, across all nations. In order to detect credit card fraud in this study, the authors will use machine learning methods such random forests, support vector machines, and gradient-boosted trees. The authors used the Synthetic Minority Oversampling Technique (SMOTE) and Random Under Sampling (RUS) sampling methods in each algorithm to compare because there was a class imbalance in this investigation. The research findings demonstrate that the author's algorithm and sample technique were successfully used, as shown by the AUC values obtained for each being &gt; 0.7. The top score in RUS was 0.7835 using the Random Forest algorithm, whereas the greatest score in SMOTE was 0.73 with the Gradient Boosted Trees approach. The Random Forest algorithm and the Random Under Sampling (RUS) technique are developed as a result of this research, and they are useful for identifying fraudulent credit card transactions.

The Imbalanced Classification of Fraudulent Bank Transactions Using Machine Learning

This article studies the development of a reliable AI model to detect fraudulent bank transactions, including money laundering, and illegal activities with goods and services. The proposed machine learning model uses the CreditCardFraud dataset and utilizes multiple algorithms with different parameters. The results are evaluated using Accuracy, Precision, Recall, F1 score, and IBA. We have increased the reliability of the imbalanced classification of fraudulent credit card transactions in comparison to the best known results by using the Tomek links resampling algorithm of the imbalanced CreditCardFraud dataset. The reliability of the results, using the proposed model based on the TPOT and RandomForest algorithms, has been confirmed by using 10-fold cross-validation. It is shown that on the dataset the accuracy of the proposed model detecting fraudulent bank transactions reaches 99.99%.

Prediction of Financial Crime Using Machine Learning

The purpose of data analytics is to uncover previously unknown patterns and make use of such patterns to help in making educated decisions across a wide range of contexts. Because of advances in modern technology and the fact that credit cards have become an easy target for fraudulent activity, the incidence of credit card fraud has considerably increased in recent years. Credit card fraud is a significant issue in the industry of financial services, and it results in annual losses of billions of dollars. The development of a fraud detection algorithm is a difficult endeavor due to the paucity of real-world transaction datasets that are available due to confidentiality concerns and the very unbalanced nature of the datasets that are publicly available. Use a dataset from the real world in conjunction with a variety of supervised machine learning algorithms to identify potentially fraudulent credit card transactions. In addition, make use of these techniques to create a super classifier through the use of ensemble learning methods. Determine which variables are the most significant and could perhaps lead to a higher level of accuracy in the identification of fraudulent credit card transactions. In addition, we evaluate and discuss the performance of a number of other supervised machine learning algorithms that are currently available in the literature in contrast to the super classifier that can be implemented.

An improved differential evolution algorithm for quantifying fraudulent transactions

Identification of fraudulent credit card transactions is a complex problem mainly due to the following factors: 1) The relative behavior of customers and fraudsters may alter over time. 2) The ratio of legitimate to fraudulent transactions is highly imbalanced, and 3) Investigators examine a small segment of transactions in a reasonable time frame. Researchers have proposed various algorithms to identify potential fraud in a new incoming transaction. However, these approaches require significant human investigator effort and are sometimes misleading. To address this issue, this paper proposes an improved multiobjective differential evolution (DE) algorithm to estimate the distribution of fraudulent transactions in a set of new incoming transactions, referred to as quantifying fraudulent transactions. Our paper has three major novelties. First, we present the problem formulation of cost-based feature selection with maximum quantification ability. Second, we improve the DE by applying effective trial vector generation algorithms to the random control parameter settings to exploit the advantage of individual DE variants. Third, we develop the maximum-relevancy-minimum-redundancy-based Pareto refining operator to enhance the self-learning ability of individuals in Pareto solutions. We compare our approach against four other modifications of DE and five state-of-the-art evolutionary algorithms on real-time credit datasets in streaming and non-streaming frameworks using hyper-volume, two-set coverage, and spread performance metrics.

Fraud Detection in Credit Cards System Using ML with AWS Stage Maker

Abstract: Credit card firms must be able to recognize fraudulent credit card transactions so that clients are not charged for products that they did not purchase. Data Science may be used to solve these issues, and coupled with machine learning, it is of utmost relevance. The goal of this project is to demonstrate how to model a data set using machine learning for credit card fraud detection. The Credit Card Fraud Detection Problem entails modelling previous credit card transactions using information from those that were later determined to be fraudulent. While the globe was under lockdown and movement was confined to an absolute emergency- millions were introduced to the world of internet shopping. The simplicity of internet buying helped ecommerce platforms generate unprecedented sales. It is not surprising that during that time, the rate of online financial fraud also skyrocketed. During the COVID-19 pandemic in 2020 compared to 2019, there was a historic increase of 225 percent in online fraud cases involving credit and debit cards.

Anomaly Detection using Generative Adversarial Network VAE

Fraudulent credit card transactions continue to be one of the problems facing businesses and banks. It causes us to lose billions of dollars each year. Designing efficient algorithms is one of the most important challenges in this field. This paper aims to propose an efficient approach that automatically detects fraud in credit card transactions using Generative Adversarial Network Variational Auto encoders. The effectiveness of the proposed method (Generative Adversarial Network VAE) has been proved in identifying fraud in actual data from transactions made by credit cards. However, the typical credit card data set presents an imbalanced classification landscape due to highly skewed class distributions. Researchers have proposed several strategies to address these imbalances, but draw backs still remain. The proposed method is tested on an open credit card fraud dataset, which contains 20 million transactions generated from a multi-agent virtual world simulation performed by IBM. Experimental results show that the VAE method performs better than traditional deep neural network methods. Through experiments, compared with the VAE and traditional fully connected neural networks, the results showed the proposed algorithm improves the classification accuracy of a minority class of imbalanced datasets.

General-purpose Unsupervised Cyber Anomaly Detection via Non-negative Tensor Factorization

Distinguishing malicious anomalous activities from unusual but benign activities is a fundamental challenge for cyber defenders. Prior studies have shown that statistical user behavior analysis yields accurate detections by learning behavior profiles from observed user activity. These unsupervised models are able to generalize to unseen types of attacks by detecting deviations from normal behavior without knowledge of specific attack signatures. However, approaches proposed to date based on probabilistic matrix factorization are limited by the information conveyed in a two-dimensional space. Non-negative tensor factorization, however, is a powerful unsupervised machine learning method that naturally models multi-dimensional data, capturing complex and multi-faceted details of behavior profiles. Our new unsupervised statistical anomaly detection methodology matches or surpasses state-of-the-art supervised learning baselines across several challenging and diverse cyber application areas, including detection of compromised user credentials, botnets, spam e-mails, and fraudulent credit card transactions.

A supervised machine learning algorithm for detecting and predicting fraud in credit card transactions

Fraudsters are now more active in their attacks on credit card transactions than ever before. With the advancement in data science and machine learning, various algorithms have been developed to determine whether a transaction is fraudulent. We study the performance of three different machine learning models: logistic regression, random forest, and decision trees to classify, predict, and detect fraudulent credit card transactions. We compare these models’ performance and show that random forest produces a maximum accuracy of 96% (with an area under the curve value of 98.9%) in predicting and detecting fraudulent credit card transactions. Thus, we recommend random forest as the most appropriate machine learning algorithm for predicting and detecting fraud in credit card transactions. Credit Card holders above 60 years were found to be mostly victims of these fraudulent transactions, with a greater proportion of fraudulent transactions occurring between the hours of 22:00GMT and 4:00GMT.