Enhanced Deep Learning Models for Secure and Efficient Cross-Border Financial Transactions

  • Authors

    • Mohammad Husain Department of Computer Science, Faculty of Computer and Information Systems, Islamic University of Madinah, Kingdom of Saudi Arabia
    • Dr. K. S. Wagh Associate Professor, Department of Computer Engineering, AISSMS Institute of Information Technology, Pune, India
    • Subhash A. Nalawade Assistant Professor, Department of Information Technology, Dr. D. Y. Patil Institute of Technology, Pimpri, Pune, India
    • Dr. Lavkush Sharma Associate Professor, Department of Computer Science and Engineering, Raja Balwant Singh Engineering Technical Campus, Bichpuri, Agra, India
    • Dr. Neeta P. Patil Associate Professor, Department of Information Technology, Thakur College of Engineering and Technology, University of Mumbai, Maharashtra, India
    • Dr. Yogita Deepak Mane Associate Professor, Department of Artificial Intelligence and Data Science, Thakur College of Engineering and Technology, University of Mumbai, Maharashtra, India
    • Dadaso T. Mane Department of Information Technology, Rajarambapu Institute of Technology, Rajaramnagar, affiliated to Shivaji University, Sangli, Maharashtra, India – 415414
    • Mohammad Rashid Hussain Assistant Professor, Department of Business Informatics, College of Business, King Khalid University, Abha-62217, Kingdom of Saudi Arabia
    https://doi.org/10.14419/bkfjbr80

    Received date: March 22, 2025

    Accepted date: May 4, 2025

    Published date: May 12, 2025

  • Cross-border financial transactions, deep learning, fraud detection, Extreme Gradient Boosting, IoT-enabled systems

  • Abstract

    As reliance on foreign financial transactions continues to increase, the number of problems regarding security vulnerabilities and the identification of dishonest activity has expanded. Traditional fraud detection systems’ incapacity to identify fraudulent activity in real-time and to adapt over time may lead to severe financial losses. Integrating modern deep learning methods offers a promising solution to improve the accuracy and speed of fraud detection. This work proposes a novel hybrid model combining Genetic Algorithm-based feature selection with a modified loss function (EL-UXGB) integrated into Extreme Gradient Boosting (XGBoost). Deep Belief Networks (DBNs), which process input features gathered from Internet of Things (IoT)-enabled devices, further enhance detection capabilities. The model was tested on a dataset of 20,000 financial transactions, 10% of which were labeled as fraudulent. The proposed method achieved a detection accuracy of 99.4%, a precision of 98.7%, and an F1-score of 98.9%, outperforming conventional methods such as Logistic Regression (85.3%) and Random Forest (91.6%). A 30% reduction in processing latency demonstrates the real-time effectiveness of the model, enabling rapid fraud detection without compromising scalability. These results validate the security and efficiency of global financial transactions and highlight the potential of deep learning approaches to address the increasing complexity of financial fraud systems. Future research will focus on further optimization and real-world deployment across international financial systems.

  • References

    1. Kumar, G. S., Kumar, S. S., Naveena, N., Selvaraj, K., Saravanan, V., & Sarala, B., “Optimized Vector Perturbation Precoding with 5G Networks and Levy Flights”, 2023 International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT), (2023), pp.1203-1208.
    2. Yuvaraj, N., Srihari, K., Dhiman, G., Somasundaram, K., Sharma, A., Rajeskannan, S. M. G. S. M. A., et al., “Nature-Inspired-Based Approach for Automated Cyberbullying Classification on Multimedia Social Networking”, Mathematical Problems in Engineering, Vol.2021, No.1, (2021), pp.6644652.
    3. Ramkumar, M., Logeshwaran, J., & Husna, T., “CEA: Certification based encryption algorithm for enhanced data protection in social networks”, Fundamentals of Applied Mathematics and Soft Computing, Vol.1, (2022), pp.161-170.
    4. Yuvaraj, N., Chang, V., Gobinathan, B., Pinagapani, A., Kannan, S., Dhiman, G., & Rajan, A. R., “Automatic detection of cyberbullying using multi-feature based artificial intelligence with deep decision tree classification”, Computers & Electrical Engineering, Vol.92, (2021), pp.107186.
    5. Gobinathan, B., Mukunthan, M. A., Surendran, S., Somasundaram, K., Moeed, S. A., Niranjan, P., et al., “A novel method to solve real time security issues in software industry using advanced cryptographic techniques”, Scientific Programming, Vol.2021, No.1, (2021), pp.3611182.
    6. Choudhry, M. D., Sundarrajan, M., Jeevanandham, S., & Saravanan, V., “Security and Privacy Issues in AI-based Biometric Systems”, AI Based Advancements in Biometrics and its Applications, (2024), pp.85-100.
    7. Zhou, K., “Financial model construction of a cross-border e-commerce platform based on machine learning”, Neural Computing and Applications, Vol.35, No.36, (2023), pp.25189-25199.
    8. Tamraparani, V., “Revolutionizing payments infrastructure with AI & ML to enable secure cross border payments”, Journal of Multidisciplinary Research, Vol.10, No.02, (2024), pp.49-70.
    9. Sekgoka, C. P., Yadavalli, V. S. S., & Adetunji, O., “Privacy-preserving data mining of cross-border financial flows”, Cogent Engineering, Vol.9, No.1, (2022), pp.2046680.
    10. Shang, H., Li, W., Li, G., Zhao, S., Li, L., & Li, Y., “Analysis and Application of Enterprise Performance Evaluation of Cross-Border E-Commerce Enterprises Based on Deep Learning Model”, Mobile Information Systems, Vol.2022, No.1, (2022), pp.1058175.
    11. Tian, X., Zhu, J., Zhao, X., & Wu, J., “Improving operational efficiency through blockchain: evidence from a field experiment in cross-border trade”, Production Planning & Control, Vol.35, No.9, (2024), pp.1009-1024.
    12. Jin, L., “Exploration of cross-border e-commerce and its logistics supply chain innovation and development path for agricultural exports based on deep learning”, Applied Mathematics and Nonlinear Sciences, Vol.9, No.1, (2024).

  • Downloads

  • How to Cite

    Husain, M. ., Wagh, D. K. S. ., Nalawade, S. A. ., Sharma, D. L. ., Patil, D. N. P. ., Mane, D. Y. D. ., Mane, D. T. ., & Hussain, M. R. . (2025). Enhanced Deep Learning Models for Secure and Efficient Cross-Border Financial Transactions. International Journal of Basic and Applied Sciences, 14(1), 280-290. https://doi.org/10.14419/bkfjbr80