This document presents a comparative study of machine learning models for credit card fraud detection. It discusses various machine learning and deep learning techniques used for credit card fraud detection systems, including neural networks, decision trees, logistic regression, random forests, convolutional neural networks, and more. It reviews related literature on using meta learning and neural networks for fraud detection. The paper aims to compare the performance of these different models for credit card fraud detection using datasets from banks containing labeled fraudulent and non-fraudulent transactions.