The popularity of credit card usage for payment has surged, but it has also led to a corresponding increase in credit card fraud, creating a significant challenge. The rapid advancement of technology and the prevalence of online transactions have provided fraudsters with numerous opportunities to engage in fraudulent activities, resulting in substantial financial losses. Consequently, it is imperative to devise effective strategies to minimize these losses. Fraudsters employ a diverse array of tactics, including deceptive phone calls, misleading SMS messages, phishing attacks, impersonations, and other methods, to illicitly obtain users’ credit card information. Their primary targets are individuals who are easily accessible and susceptible to credit card fraud. With the expansion of e-commerce and the proliferation of online platforms, the availability of online payment options has expanded significantly, thereby amplifying the risk of online fraud. To combat the escalating rates of fraud, researchers and experts are leveraging various machine learning techniques to identify and analyze fraudulent online transactions. The primary objective of these research endeavors is to develop a specialized fraud detection algorithm capable of examining historical customer transaction data and extracting behavioral patterns from the dataset. In our proposed model, we employ Autoencoders and Artificial Neural Networks to facilitate the extraction of distinctive features and the classification of anomalies.