Ensembling Logistic Regression(Lr) with Smote(Syntheic Minority over Sampling Technic for Credit Card Fraud Detection

Due to the exponential rise in electronic transactions, credit card theft is becoming a major concern for both consumers and financial institutions. The goal of this research is to create a sophisticated fraud detection system that leverages machine learning techniques. A large dataset that includes transaction details, user activities, and historical patterns is used by the suggested system. The model seeks to precisely identify and categorize fraudulent behaviors in real-time by utilizing supervised learning approaches, such as Random Forest, Support Vector Machines, and Neural Networks. In order to assess the model’s effectiveness in reducing false positives and false negatives, it is benchmarked against current fraud detection techniques. The results of this study support continuing efforts to strengthen financial systems against fraudulent activity, so improving