Credit card fraud detection is the process of identifying and preventing fraudulent transactions before they can cause financial damage. This involves using advanced algorithms and machine learning techniques to analyze transaction data in real-time and detect patterns that may indicate fraudulent activity. Effective fraud detection systems are essential for ensuring the security and integrity of the credit card payment system, protecting both financial institutions and cardholders from financial losses. The main objectives of this study are to explain the process and techniques. This study analyzes a global dataset of credit card transactions using regression analysis and artificial neural networks. A regression research found that new balance origin, new balance destination, old balance origin, transaction type, and amount all statistically effect fraud transactions, while old balance destination and transaction length do not. This study used artificial neural networks to identify credit card fraud detection properties. According to the statistics, Old Balance locations are most importantly considered for credit card fraud. This study shows that the models can detect fraudulent activity using real credit card transaction data, providing significant insights into credit card fraud detection approaches.