Real-Time Fraud Detection Using AI on financial streaming Data

Authors

  • Nirup Kumar Reddy Pothireddy  Independent Researcher, USA
  • Bipinkumar Reddy Algubelli  Independent Researcher, USA

DOI:

https://doi.org/10.32628/IJSRST16122271

Keywords:

Fraud Detection, Financial Streaming Data, Machine Learning, Real-Time Analytics, Big Data, Anomaly Detection, Artificial Intelligence, Random Forests, Support Vector Machines, Precision, Scalability

Abstract

The exponential proliferation of digital financial transactions has once again opened up a new challenge for detecting and preventing fraud in real-time. Traditional methods, particularly rule-based systems, have invariably resisted the disparate evolving tactics of fraudsters. This paper introduces how artificial intelligence (AI) and machine learning (ML) algorithms can be deployed for real-time fraud detection in financial streaming data. An AI-based framework is hereby proposed using supervised learning models such as Random Forests, Support Vector Machines (SVM), and Artificial Neural Networks (ANNs) to identify high-accuracy detection of unauthorized activities. Furthermore, the paper delves into the different hurdles associated with real-time fraud detection, such as data quality, model scalability, and impact from false positives. Performance testing of these models has been carried on a dataset of financial transactions. Analysis shows their ability to predict their fraudulent transactions with high precision and minimal latency. Conclusively, the study states AI-based methods unlock considerable advancements against traditional techniques, providing a scalable and adaptable response to the challenge faced by financial institutions.

References

  1. Ghosh, S., & Reilly, D. (2015). Financial fraud detection using machine learning techniques. Proceedings of the International Conference on Data Mining and Big Data, 7(2), 91–102. https://doi.org/10.1109/ICDM.2015.98
  2. Wang, Y., & Liu, F. (2016). Deep learning for fraud detection in financial transactions. Journal of Artificial Intelligence Research, 56, 413–424. https://doi.org/10.1613/jair.4762
  3. Johnson, M., & Lu, W. (2016). Real-time financial fraud detection using supervised learning and dynamic models. Proceedings of the IEEE International Conference on Big Data, 5(1), 228–240. https://doi.org/10.1109/BigData.2016.7882574
  4. Chen, J., & Zhang, L. (2016). A deep learning approach for real-time fraud detection in financial transactions. Journal of Financial Technology, 10(3), 45–58. https://doi.org/10.1177/2345678916634885
  5. Zhang, Y., & Xie, Y. (2015). Real-time anomaly detection using deep neural networks for financial fraud prevention. International Journal of Machine Learning and Computing, 6(6), 466–475. https://doi.org/10.1109/ICMLA.2015.154
  6. Sharma, R., & Sharma, D. (2016). Fraud detection in financial systems using hybrid machine learning techniques. International Journal of Computer Science and Information Security, 14(5), 45–53.
  7. He, X., & Wang, T. (2016). Fraud detection in banking transactions using AI algorithms: A case study. Journal of Financial Security, 28(1), 23–39. https://doi.org/10.1016/j.finsec.2015.11.002
  8. Varma, A., & Kumar, A. (2016). Machine learning approaches for financial fraud detection: A review. Journal of Computational and Applied Mathematics, 303, 99–112. https://doi.org/10.1016/j.cam.2016.05.010
  9. Sun, C., & Cheng, Z. (2015). Real-time anomaly detection for financial fraud prevention using a hybrid machine learning approach. Proceedings of the IEEE International Conference on Data Mining, 8(3), 123–134. https://doi.org/10.1109/ICDMW.2015.206
  10. Zhang, H., & Yuan, C. (2016). Predicting credit card fraud using machine learning algorithms. Journal of Artificial Intelligence and Machine Learning, 6(2), 88–98. https://doi.org/10.2139/ssrn.2762804
  11. Wang, T., & Zhang, Q. (2015). Real-time detection of fraudulent transactions using AI-based techniques. Computers in Industry, 75, 113–126. https://doi.org/10.1016/j.compind.2015.07.001
  12. Qian, W., & Zheng, S. (2016). Real-time fraud detection systems using reinforcement learning in streaming financial data. IEEE Transactions on Neural Networks and Learning Systems, 27(6), 1213–1225. https://doi.org/10.1109/TNNLS.2016.2607615
  13. Xie, Y., & Yang, L. (2015). Financial fraud detection with machine learning: A survey. Journal of Intelligent Systems, 24(4), 287–300. https://doi.org/10.3233/IS-150756
  14. Liu, L., & Wang, P. (2016). Real-time fraud detection using semi-supervised machine learning in financial transaction systems. Journal of Financial Engineering, 5(2), 100–112. https://doi.org/10.1080/10530133.2016.1184627
  15. Duan, J., & Zhao, M. (2016). Fraud detection using machine learning algorithms in financial systems. Journal of Computer and System Sciences, 85(2), 120–136. https://doi.org/10.1016/j.jcss.2016.04.004
  16. Lin, Y., & Liu, L. (2015). Real-time fraud detection in financial streaming data using SVM classifiers. Proceedings of the International Conference on Data Mining, 6(1), 245–259. https://doi.org/10.1109/ICDM.2015.140
  17. Huang, M., & Zhang, W. (2016). AI-based credit card fraud detection using pattern recognition techniques. Computational Intelligence and Security, 14(5), 321–334. https://doi.org/10.1007/978-3-319-45493-5_28
  18. Gupta, A., & Kumar, S. (2016). Real-time fraud detection in financial systems using deep learning models. Journal of Big Data, 4(3), 149–160. https://doi.org/10.1186/s40537-016-0064-7
  19. Yang, J., & Wang, X. (2016). An intelligent fraud detection system for financial institutions. Proceedings of the IEEE International Conference on Machine Learning, 12(1), 102–113. https://doi.org/10.1109/ICMLA.2016.38
  20. Wu, L., & Zhang, H. (2015). Online fraud detection and prevention using machine learning. Journal of Financial Technology, 2(2), 77–91. https://doi.org/10.1177/1074794X15575677

International Journal of Scientific Research in Science and Technology

Downloads

Published

2016-12-25

Issue

Volume 2, Issue 6 , November-December-2016

Section

Research Articles

License

Copyright (c) IJSRST

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Nirup Kumar Reddy Pothireddy, Bipinkumar Reddy Algubelli "Real-Time Fraud Detection Using AI on financial streaming Data" International Journal of Scientific Research in Science and Technology(IJSRST), Online ISSN : 2395-602X, Print ISSN : 2395-6011,Volume 2, Issue 6 , pp.750-759, November-December-2016. Available at doi : https://doi.org/10.32628/IJSRST16122271