Credit card fraud Detection using Feature select method and improved machine learning algorithm

In todays digital age, credit card fraud has become a serious issue, posing financial risks to individuals, businesses, and financial institutions alike. Detecting credit card fraud is crucial to limiting these risks and securing financial systems. This article presents an improved support vector machine (SVM)-based approach that integrates an advanced feature selection method for identifying fraudulent activities. By using a binary genetic algorithm and cross-entropy, our feature selection approach identifies key attributes and evaluates their relevance to the target variable. The SVM classification model then performs the final classification, with its hyperparameters optimized through the particle swarm optimization (PSO) technique. Experimental results on the Credit Card Fraud Detection dataset demonstrate the effectiveness of this method, achieving an impressive accuracy of 99.99%. By combining advanced feature selection with optimization techniques, this approach enhances the accuracy and efficiency of credit card fraud detection, offering a practical solution to combat fraud in financial systems.