Edge Computing–Enabled Intelligent Financial Auditing: An Advanced Real-Time Framework for Automated Fraud Detection, Predictive Accounting Analytics, and Financial Risk Assessment

Abstract

Purpose: The increasing volume, velocity, and complexity of digital financial transactions have reduced the effectiveness of conventional auditing systems that depend on centralized processing, periodic examination, and static rule-based controls. This study develops an edge computing–enabled intelligent financial auditing framework for real-time fraud detection, predictive accounting analytics, and dynamic financial risk assessment.

Design/Methodology/Approach. The framework integrates distributed edge nodes, secure financial gateways, machine learning, attention-based deep learning, explainable artificial intelligence, and human-in-the-loop audit validation. A multi-institutional dataset comprising 285,000 anonymized transactions from 18,750 individual and corporate accounts collected over three years was used for framework evaluation. Following missing-value treatment, normalization, feature selection, class balancing, and temporal segmentation, the data were divided into training, validation, and testing subsets using a 70:15:15 ratio.

Findings. The proposed edge-enabled attention-based model achieved 97.4% accuracy, 96.8% precision, 97.1% recall, a 96.9% F1-score, and a 0.991 ROC–AUC, exceeding the best-performing benchmark, XGBoost, which produced 94.6% accuracy and a 0.967 ROC–AUC. Edge-based processing reduced average fraud-detection latency from 2.84 seconds to 0.41 seconds, lowered financial-data transmission requirements by 38.7%, and increased high-risk account identification by 21.6% compared with centralized auditing. Predictive analytics achieved a mean absolute percentage error of 6.8% for cash-flow forecasting and identified 93.5% of emerging financial-risk events before critical thresholds were reached.

 Research Limitations. The dataset, while multi-institutional, may not fully represent all geographic regions or financial sectors. Future studies should incorporate cross-border payments, digital wallets, and cryptocurrency transactions.

Practical Implications. The framework offers a scalable and privacy-aware foundation for banks, accounting organizations, and audit firms pursuing secure real-time digital transformation. It can strengthen continuous assurance, accelerate fraud intervention, improve accounting forecasts, reduce audit workload, and support proactive financial governance.

References

Ahmad, B., Ali, S., Muneer, M., Fatima, A., & Abbas, N. (2025). Wind energy integration into the SAARC region: A comprehensive review of optimal wind sites for a sustainable super smart grid. Dialogue Social Science Review, 3(2), 488–515. https://doi.org/10.5281/zenodo.20999213

Ahmad, B., Jillani, S. A., Rafique, M., & Soomro, A. A. (2026). Design and monitoring of a tree-inspired vertical axis wind turbine for efficient urban wind utilization. In 2026 1st International Conference on Innovations in Information and Communication Technologies (IICT) (pp. 1–6). IEEE. https://doi.org/10.1109/IICT68374.2026.11468465

Ahmad, B., Majeed, M. K., Soomro, A. A., & Jillani, S. A. (2026). Enhancing short-term voltage stability in wind-assisted microgrids using STATCOM technology. In 2026 1st International Conference on Innovations in Information and Communication Technologies (IICT) (pp. 1–6). IEEE. https://doi.org/10.1109/IICT68374.2026.11468707

Akter, M. S. (2025). AI-enhanced financial information systems for real-time fraud detection and cash flow optimization in US logistics and retail sectors. American Journal of Scholarly Research and Innovation, 4(1), 813–855.

Al Montaser, M. A., & Bannett, M. (2025). Beyond anomaly detection: Redesigning real-time financial fraud systems for multi-channel transactions in emerging markets. Baltic Journal of Multidisciplinary Research, 2(3), 1–17.

Alatawi, M. N. (2025). EdgeGuard-IoT: 6G-enabled edge intelligence for secure federated learning and adaptive anomaly detection in Industry 5.0. Computers, Materials & Continua, 85(1), 695–727. https://doi.org/10.32604/cmc.2025.066606

Akinsanya, M. O., Bello, A. B., & Adeusi, O. C. (2023). A comprehensive review of edge computing approaches for secure and efficient data processing in IoT networks. Communication in Physical Sciences, 9(4), 870–877.

Alves, J. F. R. M. (2025). Privacy-aware explainable AI framework for multi-modal big data analytics in real-time payment fraud detection and pharmaceutical network intelligence. International Journal of Research and Applied Innovations, 8(Special Issue 1), 86–95.

Amirineni, S., & Abhilash, K. S. (2025). AI-driven fraud detection in IoT-enabled payment ecosystems: Challenges, hybrid edge-cloud framework, and emerging trends. In 2025 6th International Conference on Electronics and Sustainable Communication Systems (ICESC) (pp. 1406–1413). IEEE. https://doi.org/10.1109/ICESC65114.2025.11212351

Aroh, I. (2025). Developing explainable AI-enabled edge cloud framework for financial analytics and intelligent risk governance. International Journal of Science, Research and Technology, 8(6), 15431–15439.

Bello, O. A., Ogundipe, A., Mohammed, D., Adebola, F., & Alonge, O. A. (2023). AI-driven approaches for real-time fraud detection in US financial transactions: Challenges and opportunities. European Journal of Computer Science and Information Technology, 11(6), 84–102.

Brinkkemper, S. (2026). Intelligent cloud-native financial analytics frameworks for fraud detection risk prediction and autonomous governance systems. International Journal of Computer Technology and Electronics Communication, 9(3), 1080–1095.

Burugulla, J. K. R. (2024). The future of digital financial security: Integrating AI, cloud, and big data for fraud prevention and real-time transaction monitoring in payment systems. MSW Management Journal, 34(2), 711–730.

Darwish, S. M., El-Naggar, S., & Elkaffas, S. M. (2026). Securing financial transactions: Exploring the role of lightweight blockchain-enabled deep learning for fraud detection in FinTech systems. Cybersecurity, 9(1), Article 8. https://doi.org/10.1186/s42400-025-00436-8

Fonkem, B. N. (2025). AI-powered risk scoring models for real-time fraud detection in digital banking ecosystems. Journal of Computational Analysis and Applications, 34(11), 349–371.

Garg, V., & Mishra, G. (2026). Smart financial surveillance: Blockchain and explainable AI for fraud detection in smart healthcare organizations. In Blockchain solutions for securing Internet of Things networks (pp. 225–266). Wiley. https://doi.org/10.1002/9781394417131.ch9

Gkegkas, M., Kydros, D., & Pazarskis, M. (2025). Using data analytics in financial statement fraud detection and prevention: A systematic review of methods, challenges, and future directions. Journal of Risk and Financial Management, 18(11), Article 598. https://doi.org/10.3390/jrfm18110598

Hasibuan, A. A., & Nasution, M. I. (2025). The impact of real-time and continuous auditing on financial transparency and fraud detection: A systematic literature review. In Proceedings of International Conference on Islamic Community Studies (pp. 415–428).

Ikeh, C. O. (2025). Hybrid AI frameworks for real-time fraud detection in cross-border digital payment ecosystems. International Journal of Advance Research Publication and Reviews, 2(5), 21–44. https://doi.org/10.5281/zenodo.15386508

Kalaiselvi, R. (2026). Explainable AI models for cloud-based fraud detection risk assessment and secure financial decision intelligence. International Journal of Technology, Management and Humanities, 12(2), 35–46.

Khan, I., Japa, C., Muthukumarasamy, K., & Gadam, H. (2025). Real-time financial fraud detection with cognitive 6G networks and distributed AI autonomous risk management. Advances in Consumer Research, 2, 4063–4072.

Lambropoulos, G., Mitropoulos, S., & Douligeris, C. (2026). Emerging technologies in financial services: From virtualization and cloud infrastructures to edge computing applications. Computers, 15(1), Article 41. https://doi.org/10.3390/computers15010041

Mollah, M. A. R. (2026). AI-driven business intelligence for real-time fraud risk monitoring in digital payment platforms: A framework-based review. International Journal of Scientific Interdisciplinary Research, 7(1), 527–580. https://doi.org/10.63125/0ef34271

Moreau, A. L. (2025). AI-enabled real-time financial fraud detection and encryption impact analysis in high-performance cloud-based enterprise networks. International Journal of Computer Technology and Electronics Communication, 8(6), 11763–11770. https://doi.org/10.15680/IJCTECE.2025.0806021

Naaz, J., Patel, H., & Syed, Z. (2026). Cloud-native event-driven orchestration architecture for real-time fraud and sanctions screening. American International Journal of Computer Science and Technology, 8(4), 12–24. https://doi.org/10.63282/3117-5481/AIJCST-V8I4P102

Nawaz, Y., & Musah, M. (2025). Enhancing FinTech security and efficiency: A unified framework for real-time fraud detection using deep neural networks. https://doi.org/10.13140/RG.2.2.11842.29126

Nofel, M., Marzouk, M., Elbardan, H., Saleh, R., & Mogahed, A. (2024). From sensors to standardized financial reports: A proposed automated accounting system integrating IoT, blockchain, and XBRL. Journal of Risk and Financial Management, 17(10), Article 445. https://doi.org/10.3390/jrfm17100445

Nowak, A. M. (2022). Secure AI-enabled cloud platforms for healthcare image analysis and financial fraud detection across web applications and 5G networks. International Journal of Engineering & Extended Technologies Research (IJEETR), 4(5), 5333–5341.

Pan, X. (2025). Detection and compliance in financial management via 6G-enabled standardized AI-powered digital twins. IEEE Communications Standards Magazine.

Prabha, M., Nandhini, S., Dayanidhy, M., & Pradeep, R. (2025). Edge-AI integrated secure wireless IoT architecture for real-time healthcare monitoring and federated anomaly detection. Scientific Reports, 16(1), 574.

Rajput, A., & Katamba, I. (2024). Leveraging artificial intelligence and big data in public accounting: Redefining audit practices and financial reporting. International Journal of Research Publication and Reviews, 5(11), 5516–5531. https://doi.org/10.55248/gengpi.5.1124.3341

Ramli, A. I. B. (2024). Big data and artificial intelligence to develop advanced fraud detection systems for the financial sector. International Journal of Advanced Cybersecurity Systems, Technologies, and Applications, 8(12), 31–44.

Sethupathy, U. K. A. (2025). Risk-aware AI models for financial fraud detection: Scalable inference from big transactional data. International Journal of Intelligence Science, 15(4), 162–183. https://doi.org/10.4236/ijis.2025.154009

Singh, D. (2025). Explainable graph-based AI for real-time fraud detection in distributed healthcare claims processing systems. International Journal of Science, Technology and Convergence, 7(7).

Timileyin, O. (2026). Secure edge AI frameworks for real-time fraud detection in financial and digital banking systems.

Zakaria, R. M., Rahman, M. M., Rahman, H., Rafi, M. A., Minto, A., Hossain, M. S., & Saimon, S. I. (2025). Detecting financial fraud in real-time transactions using graph neural networks and anomaly detection techniques. Journal of Economics, Finance and Accounting Studies, 7(6), 1–13. https://doi.org/10.32996/jefas.2025.7.6.1

Zhong, H., Yang, D., Shi, S., Wei, L., & Wang, Y. (2024). From data to insights: The application and challenges of knowledge graphs in intelligent audit. Journal of Cloud Computing, 13(1), Article 114. https://doi.org/10.1186/s13677-024-00674-0

Zhukabayeva, T., Zholshiyeva, L., Karabayev, N., Khan, S., & Alnazzawi, N. (2025). Cybersecurity solutions for industrial Internet of Things–edge computing integration: Challenges, threats, and future directions. Sensors, 25(1), Article 213. https://doi.org/10.3390/s25010213