As is well-known, the number of people making purchases with credit cards has skyrocketed. Fraudulent activities are on the rise in tandem with the widespread use of credit cards. Consequently, credit card transactions in the real world are at the heart of this project's scope and content. Without crediting their own accounts or crediting from other accounts, the intruders want to acquire products/goods. For credit card fraud detection, there were formerly several unsupervised machine learning algorithms like ANN that were less accurate. This research combines supervised machine learning techniques such as Random Forest and Cart algorithms in order to improve the model's accuracy. As a result, the approaches' performance is judged by their accuracy, specificity and sensitivity and precision.

.