Model Based on Credit Card Fraud Detection Using Machine Learning

People can use credit cards to offer a convenient and effective facility for online transactions. Utilization of credit cards has increased, and with that, so has the potential for credit card fraud. Online credit card use has dramatically increased as a result of the e-commerce sector’s explosive growth. As technology advances, banks find it harder to detect fraud. In addition, as new security features are added to credit card transactions, fraudsters are also coming up with new ways to steal money. Machine learning plays a significant role in predicting fraud transactions as a means of resolving this issue. The European Bank dataset is used in this paper. This dataset, which includes a total of 2,843,315 credit card transactions, was collected from the Kaggle Web site. Logistic regression, random forest, isolation forest algorithms, K-nearest neighbor, support vector machine (SVM), local outlier factor, and multiplier perception are just a few of the seven machine learning methodologies used in this paper.