Backend Latency Optimization in Real-Time Fraud Detection Systems

Authors

  • Avinash Rahul Gudimetla University of Central Missouri, USA Author

DOI:

https://doi.org/10.32628/CSEIT251112349

Keywords:

Edge Computing Optimization, Fraud Detection Systems, Latency Optimization, Performance Benchmarking, Real-time Processing

Abstract

This technical article explores advanced optimization techniques for backend systems in real-time fraud detection, focusing on achieving minimal latency while maintaining high accuracy in transaction processing. Through comprehensive implementation of in-memory databases, multi-level caching strategies, and asynchronous processing pipelines, the system achieved a 99th percentile response time of 212 microseconds, representing a 77% improvement over traditional architectures. The integration of serverless computing for dynamic scaling enabled handling of up to 228,000 transactions per second, while edge computing deployment reduced network latency from 95ms to 22.3ms per transaction. The system maintained 99.985% fraud detection accuracy while reducing CPU utilization from 82% to 38% and memory utilization from 88% to 52%. The article presents detailed performance benchmarks from production environments, demonstrating these significant improvements in response times, throughput, and resource utilization. Additionally, the article addresses implementation challenges and solutions across different architectural layers, from data storage to model deployment, while considering crucial aspects such as privacy preservation and regulatory compliance in financial systems. The optimizations resulted in a 37% reduction in operational costs while maintaining strict compliance with data protection regulations.

Downloads

References

Abdulwahab Ali Almazroi, et al., "Online Payment Fraud Detection Model Using Machine Learning Techniques", IEEE Access, vol. 11, pp. 133261-133273, 2023. URL: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10341223

Marcus Basalla, et al., "On Latency of E-Commerce Platforms", Journal of Organizational Computing and Electronic Commerce 31(1):1-17, 2021. URL: https://www.researchgate.net/publication/350600983_On_Latency_of_E-Commerce_Platforms

Abdullah Talha Kabakus, et al., "A performance evaluation of in-memory databases," Journal of King Saud University - Computer and Information Sciences, Volume 29, Issue 4, October 2017, Pages 520-525. URL: https://www.sciencedirect.com/science/article/pii/S1319157816300453

Jun Wook Heo, et al., "Blockchain Storage Optimisation With Multi-Level Distributed Caching," IEEE Transactions on Network and Service Management, 2022. URL: https://ieeexplore.ieee.org/abstract/document/9964121

Akhilesh Kota, et al., "Real-Time Ai-Powered Fraud Detection: A Microservices Approach," International Journal Of Computer Engineering & Technology 15(6):2011-2024. URL: https://www.researchgate.net/publication/387583433_REAL-TIME_AI-POWERED_FRAUD_DETECTION_A_MICROSERVICES_APPROACH

Goutham Sabbani, "Cloud-Based Fraud Detection Systems in Financial Institutions," Journal of Scientific and Engineering Research, 2022, 9(8):147-150. URL: https://jsaer.com/download/vol-9-iss-8-2022/JSAER2022-9-8-147-150.pdf

Josh Sammu, "Optimizing Cold Start Times in Serverless Computing," International Journal of Cloud Computing, vol. 12, no. 4, pp. 234-249, 2018. URL: https://www.researchgate.net/publication/388178076_Optimizing_Cold_Start_Times_in_Serverless_Computing

Bharath Kumar Gaddam, "Edge Computing: Revolutionizing Real-Time Financial Analytics throughLow-Latency Processing," International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2024. URL: https://ijsrcseit.com/index.php/home/article/view/CSEIT241061143/CSEIT241061143

Zheng Zhou, et al., "A Deployment Method for Motor Fault Diagnosis Application Based on Edge Intelligence," Sensors, vol. 25, no. 1, pp. 9-28, 2024. URL: https://www.mdpi.com/1424-8220/25/1/9

Waleed Hilal, et al., "Financial Fraud: A Review of Anomaly Detection Techniques and Recent Advances," Expert Systems with Applications, Volume 193, 1 May 2022, 116429. URL: https://www.sciencedirect.com/science/article/pii/S0957417421017164

Santoshkumar Anchoori, et al., "Optimizing Real-Time Data Pipelines For Financial Fraud Detection: A Systematic Analysis Of Performance, Scalability, And Cost Efficiency In Banking Systems," International Journal Of Computer Engineering & Technology 15(6):878-894, 2024. Url: https://www.researchgate.net/publication/387274000_OPTIMIZING_REAL-TIME_DATA_PIPELINES_FOR_FINANCIAL_FRAUD_DETECTION_A_SYSTEMATIC_ANALYSIS_OF_PERFORMANCE_SCALABILITY_AND_COST_EFFICIENCY_IN_BANKING_SYSTEMS

Vadisena Venkata Krishna Reddy, et al., "Deep learning-based credit card fraud detection in federated learning," Expert Systems with Applications, Volume 255, Part A, 1 December 2024, 124493. URL: https://www.sciencedirect.com/science/article/abs/pii/S0957417424013605

Downloads

Published

23-02-2025

Issue

Section

Research Articles

How to Cite

Backend Latency Optimization in Real-Time Fraud Detection Systems. (2025). International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 11(1), 3295-3308. https://doi.org/10.32628/CSEIT251112349