In the financial industry, detecting credit card fraud is a crucial task because of the increasing number of fraudulent transactions that can result in major losses. Credit cards serve as a convenient and efficient means for conducting online transactions. However, the rise in credit card usage has concurrently led to an increase in instances of misuse. Credit card fraud results in substantial financial losses for both consumers and financial institutions. This research aims to identify such fraudulent activities, considering the availability of public data, the challenges posed by class imbalance, the evolving methods for fraud, and the prevalence of false positives. These three techniques are applied to the raw and preprocessed data. This project is done using Python and the proposed model surpasses existing machine learning and deep learning algorithms in solving credit card fraud detection challenges. Additionally, experiments were conducted to balance the dataset.