Passive optical network optimization and analysis using toward trustworthy fintech: a blockchain-BiLSTM approach for accurate, auditable fraud detection
-
Ruchin Kumar
Abstract
FinTech fraud has become a pressing challenge as financial services increasingly migrate online. While digital platforms have transformed banking, payments, lending, and insurance, they have also expanded the attack surface for fraudulent activities. Industry studies estimate that organizations lose about 5 % of annual revenue to fraud, with global losses projected at US$5–5.5 trillion annually. The surge in digital payments further exacerbates this problem; for instance, the U.S. Automated Clearing House (ACH) processed over 33 billion transactions in 2024, exceeding manual auditing capacity. Insurance fraud, particularly in healthcare, also remains substantial, consuming 3–10 % of expenditures. To address these challenges, this paper proposes an integrated fraud-detection framework that combines blockchain technology with bidirectional long short-term memory (BiLSTM) neural networks. Blockchain offers transparent, tamper-proof, and auditable ledgers for secure data sharing, while BiLSTM models capture sequential dependencies in transactions by learning from both past and future contexts. This integration overcomes the limitations of rule-based, isolated AI, and purely cryptographic methods that often fail against sophisticated schemes. Experimental evaluation on simulated credit card and lending datasets demonstrates significant improvements in fraud detection accuracy, auditability, and false-positive reduction. The proposed blockchain–BiLSTM framework enhances trust, compliance, scalability, and security, providing a robust foundation for next-generation FinTech fraud prevention.
Acknowledgments
Thanks to all my co author for the support.
-
Research ethics: Not applicable.
-
Informed consent: We all are fully responsible for this paper.
-
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: The author states no conflict of interest.
-
Research funding: None declared.
-
Data availability: Not applicable.
References
1. Feng, P. Hybrid BiLSTM-transformer model for identifying fraudulent transactions in financial systems. J Comput Sci Softw Appl 2025;5.Search in Google Scholar
2. Asiri, A, Somasundaram, K. Graph convolution network for fraud detection in bitcoin transactions. Sci Rep 2025;15:11076. https://doi.org/10.1038/s41598-025-95672-w.Search in Google Scholar PubMed PubMed Central
3. Kannadasan, T. Financial sentiment analysis model using ebola optimization search algorithm and Bi-directional gated recurrent unit. In: 2025 3rd International Conference on Integrated Circuits and Communication Systems (ICICACS). IEEE; 2025:1–6 pp.10.1109/ICICACS65178.2025.10967922Search in Google Scholar
4. Sudharson, K, Varsha, S, Rajalakshmi, S, Rajalakshmi, D, Santhiya, R. Financial transactional fraud detection using a hybrid BiLSTM with attention-based autoencoder. Int Res J Multidiscip Technovation 2025;7:135–47. https://doi.org/10.54392/irjmt25211.Search in Google Scholar
5. Qu, Y, Si, X, Kang, H, Zhou, H. Detecting Ethereum Ponzi scheme based on hybrid sampling for smart contract. Comput Mater Continua (CMC) 2025;82. https://doi.org/10.32604/cmc.2024.057368.Search in Google Scholar
6. Wang, S. Intelligent BiLSTM-Attention-IBPNN method for anomaly detection in financial auditing. IEEE Access 2024. https://doi.org/10.1109/access.2024.3420243.Search in Google Scholar
7. Zhu, X. Construction of financial auditing teaching mode based on artificial intelligence expert system. Bol Tec 2017;55:743–7.Search in Google Scholar
8. Zhao, H, Wang, Y. A big data-driven financial auditing method using convolution neural network. IEEE Access 2023;11:41492–502. https://doi.org/10.1109/access.2023.3269438.Search in Google Scholar
9. Ashtiani, MN, Raahemi, B. Intelligent fraud detection in financial statements using machine learning and data mining: a systematic literature review. IEEE Access 2022;10:72504–25. https://doi.org/10.1109/access.2021.3096799.Search in Google Scholar
10. Almazroi, AA, Ayub, N. Online payment fraud detection model using machine learning techniques. IEEE Access 2023;11:137188–203. https://doi.org/10.1109/access.2023.3339226.Search in Google Scholar
11. Taher, SS, Ameen, SY, Ahmed, JA. Advanced fraud detection in blockchain transactions: an ensemble learning and explainable ai approach. Eng Technol Appl Sci Res 2024;14:12822–30. https://doi.org/10.48084/etasr.6641.Search in Google Scholar
12. Kanamori, S, Abe, T, Ito, T, Emura, K, Wang, L, Yamamoto, S, et al.. Privacy-preserving federated learning for detecting fraudulent financial transactions in Japanese banks. J Inf Process 2022;30:789–95. https://doi.org/10.2197/ipsjjip.30.789.Search in Google Scholar
13. Alghofaili, Y, Albattah, A, Rassam, MA. A financial fraud detection model based on LSTM deep learning technique. J Appl Secur Res 2020;15:498–516. https://doi.org/10.1080/19361610.2020.1815491.Search in Google Scholar
14. Toufik, G, Khaldi, Y, Pandey, PS, &Abusal, YA. Advanced fraud detection in Card-Based financial systems using a bidirectional Lstm-Gru ensemble model. Appl Comput Sci 2024;20. https://doi.org/10.35784/acs-2024-28.Search in Google Scholar
15. Zou, C, Yuan, A, Hu, J. BiLSTM-based anomaly detection in multivariate time series with attention mechanism and dual analysis. In: 2024 IEEE 7th International Conference on Information Systems and Computer Aided Education (ICISCAE). IEEE; 2024:379–84 pp.10.1109/ICISCAE62304.2024.10761506Search in Google Scholar
16. Zou, F, Hu, S, Yu, W, Yan, Z, Chan, S. Research on financial fraud text classification based on PET-BiLSTM. In: Proceedings of the 2024 3rd International Conference on Cyber Security, Artificial Intelligence and Digital Economy; 2024:341–5 pp.10.1145/3672919.3672982Search in Google Scholar
17. Hashemi, SK, Mirtaheri, SL, Greco, S. Fraud detection in banking data by machine learning techniques. IEEE Access 2022;11:3034–43. https://doi.org/10.1109/access.2022.3232287.Search in Google Scholar
18. Hernandez Aros, L, Bustamante Molano, LX, Gutierrez-Portela, F, Moreno Hernandez, JJ, Rodríguez Barrero, MS. Financial fraud detection through the application of machine learning techniques: a literature review. Humanit Soc Sci Commun 2024;11:1–22. https://doi.org/10.1057/s41599-024-03606-0.Search in Google Scholar
19. Alenizi, A, Mishra, S, &Baihan, A. Enhancing secure financial transactions through the synergy of blockchain and artificial intelligence. Ain Shams Eng J 2024;15:102733. https://doi.org/10.1016/j.asej.2024.102733.Search in Google Scholar
20. Addula, SR, Meduri, K, Nadella, GS, &Gonaygunta, H. AI and blockchain in finance: opportunities and challenges for the banking sector. Int J Adv Res Comput Commun Eng 2024;13:184–90. https://doi.org/10.17148/ijarcce.2024.13231.Search in Google Scholar
21. Paramesha, M, Rane, NL, Rane, J. Artificial intelligence, machine learning, deep learning, and blockchain in financial and banking services: a comprehensive review. Partn Univers Multidiscip Res J 2024;1:51–67.10.2139/ssrn.4855893Search in Google Scholar
22. Anwar, S, Shukla, VK, Rao, SS, Sharma, BK, Sharma, P. Framework for financial auditing process through blockchain technology, using identity based cryptography. In: 2019 Sixth HCT Information Technology Trends (ITT). IEEE; 2019:099–103 pp.10.1109/ITT48889.2019.9075120Search in Google Scholar
23. Kola, B. Federated learning for privacy-preserving AI. In: Sustainable Financial Systems; 2023.Search in Google Scholar
24. Bello, OA, Olufemi, K. Artificial intelligence in fraud prevention: exploring techniques and applications challenges and opportunities. Comput Sci IT Res J 2024;5:1505–20. https://doi.org/10.51594/csitrj.v5i6.1252.Search in Google Scholar
25. Wu, Y. Enterprise financial sharing and risk identification model combining recurrent neural networks with transformer model supported by blockchain. Heliyon 2024;10. https://doi.org/10.1016/j.heliyon.2024.e32639.Search in Google Scholar PubMed PubMed Central
26. GR, J, P, AI. Attention layer integrated BiLSTM for financial fraud prediction. Multimed Tool Appl 2024;83:80613–29. https://doi.org/10.1007/s11042-024-18764-1.Search in Google Scholar
27. Ashfaq, T, Khalid, R, Yahaya, A, Aslam, S, Alsafari, S, Hameed, I, et al.. A machine learning and blockchain bases efficient fraud detection mechanism. Sensors 2022;22:7162. https://doi.org/10.3390/s22197162.Search in Google Scholar PubMed PubMed Central
28. Koutroumpis, J. Electric vehicles, fintech and fraud: a multi-sector LSTM analysis. Procedia Comput Sci 2021;187:185–94.Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
