In order In the era of digital finance, credit card fraud detection has become a critical issue for financial institutions and consumers alike. This study proposes a novel approach to credit card fraudulent classification by integrating a Stacked Convolutional Neural Network (CNN) with the Flower Pollination Algorithm (FPA). The Stacked CNN is the deep learning model that leverages multiple layers of CNNs to extract complex patterns from data, making it highly effective for image and pattern recognition tasks.The Flower Pollination Algorithm, inspired by the natural process of pollination, is a Meta heuristic optimization algorithm that has shown promising results in various optimization problems. The proposed methodology combines the strengths of both the Stacked CNN and the FPA to create a robust framework for credit card fraud detection. The Stacked CNN is employed to analyze transaction data, identifying patterns indicative of fraudulent activities. The FPA is then used to optimize the CNN's parameters, ensuring that the model is not only accurate but also efficient in its detection capabilities.Through extensive experiments and comparisons with traditional machine learning models, this study demonstrates that the integration of Stacked CNN with FPA significantly improves the accuracy and efficiency of credit card fraud detection.The proposed methodology not only outperforms existing models in terms of detection accuracy but also reduces the computational complexity, making it a practical solution for real-world applications.This research contributes to the ongoing efforts to enhance security measures in the financial sector and provides a foundation for further research in the application of deep learning and optimization algorithms in fraud detection.