An enhanced AI-based model for financial fraud detection

The research seeks to identify complex fraudulent activities. Artificial intelligence (AI) techniques, such as machine learning and deep learning, have shown significant potential in enhancing the accuracy and efficiency of fraud detection models. This study introduces a novel AI-based fraud detection model that combines both supervised and unsupervised learning methods. The proposed machine learning system uses these techniques to detect fraudulent transactions. The supervised learning component is trained using a labeled dataset that includes both fraudulent and non-fraudulent transactions. The dataset used in the research contains 284,807 credit card transactions. After preparing the data, four Python-based models were developed. The K-Nearest Neighbors (KNN) model successfully predicted 99.94% of credit card transactions as valid or fraudulent. A random forest (RF) model was also used to assess the legitimacy of transactions, achieving an accuracy score of 99.96% correctly classifying nearly all data points. The Support Vector Machine (SVM) model achieved 99.94% accuracy, misclassifying only 51 cases. The logistic regression (LR) model attained an accuracy of 99.92% with 70 misclassifications and 99.91% with 77 misclassifications. These models demonstrate high accuracy and efficiency.