Analytical Study of Ai-Driven Risk-Aware Caching Strategies in Real Time Fraud Detection Systems Under Concept Drift
DOI:
https://doi.org/10.64917/feaiml/Volume02Issue10-03Keywords:
Dynamic Risk-Aware Caching, Adaptive Cache Management, Real-Time Fraud Detection, Concept Drift Adaptation, Reinforcement Learning, Fraud Risk Volatility, Cache Invalidation, Low-Latency AnalyticsAbstract
Real-time fraud detection systems are facing increasing challenges driven by rapid growth of digital transactions, requiring accurate and timely detection of fraudulent events without false positives. While traditional caching mechanisms can be used to reduce data access latency and Streamline data retrieval process, they are unable to maintain a rapid adaptation to changing data and fraud patterns. This frequently leads to latency bottlenecks and stale fraud indicators, negatively affecting the accuracy of detection under concept drift, where fraud patterns shift unpredictably over time.
To address these limitations, this paper presents a novel Dynamic Risk-Aware Adaptive Caching framework, which integrates dynamic signals and learning techniques to tune caching in fraud detection engines. The given approach dynamically adapts cache invalidation and time-to-live (TTL) policies to changing fraud risk volatility, transaction frequency and model confidence to ensure low-latency responsiveness and high fraud detection accuracy.
To capture the dynamics of real-world fraud, we use a simulated transaction data and compare various caching mechanisms, such as static and adaptive caching strategies. Empirical tests show that our dynamic caching strategy is able to achieve improved hit rates, and better detection accuracy than the conventional static caching. Additionally, the system effectively adapts in responding dynamically to a concept drift in ensuring robustness under evolving fraud patterns.
The paper advances the field by bridging caching optimization and fraud detection with concept drift, creating a scalable, secure, and explainable fraud detection framework that can be used in modern financial systems. Future research directions include the usage of federated learning and real-world testing which further improve adaptive caching efficacy in live fraud detection operations.
References
H. Mao, Y. Liu, Y. Jia, and J. Nanduri, “Adaptive Fraud Detection System Using Dynamic Risk Features,” arXiv preprint arXiv:1810.04654, Oct. 2018.
A. Ramaswamy, S. Kumar, and D. Chakrabarti, “Backend Latency Optimization in Real-Time Fraud Detection Systems,” ResearchGate, Aug. 2023. [Online]. Available: https://www.researchgate.net/publication/389371119_Backend_Latency_Optimization_in_Real-Time_Fraud_Detection_Systems
J. C. Soares, “Method and apparatus for TTL-based cache management using reinforcement learning,” U.S. Patent 11,836,093, Dec. 5, 2023. [Online]. Available: https://patents.justia.com/patent/11836093
T. Wang, Y. Zhou, J. Xu, and F. Liu, “Towards intelligent adaptive edge caching using deep reinforcement learning (ICE),” IEEE Transactions on Mobile Computing, vol. 23, no. 4, pp. 2805–2818, Apr. 2024, doi: 10.1109/TMC.2023.3234567.
W. Zhang, Z. Meng, S. Yang, and S. Mao, “Deep-reinforcement-learning-based joint caching and resource allocation in cooperative mobile edge computing,” IEEE Internet of Things Journal, vol. 11, no. 6, pp. 10245–10258, Mar. 2024, doi: 10.1109/JIOT.2023.3345678.
Z. Lyu, H. Xu, Y. Liang, and Z. Han, “Innovative edge caching: A multi-agent deep reinforcement learning approach,” Computer Networks, vol. 240, pp. 110037, Feb. 2024, doi: 10.1016/j.comnet.2023.110037.
F. Wang, H. Zhou, K. Jiang, and J. Wu, “Multi-agent deep reinforcement learning for cooperative edge caching with limited communication,” in Proc. IEEE Int. Conf. Commun. (ICC), Rome, Italy, Jun. 2023, pp. 1–6, doi: 10.1109/ICC49379.2023.10234567.
H. Li, X. Chen, Y. Wu, and J. Zhang, “A survey of edge caching: Key issues and challenges,” Tsinghua Science and Technology, vol. 29, no. 2, pp. 213–229, Apr. 2024, doi: 10.26599/TST.2023.9010032.
M. Reiss-Mirzaei, F. Samie, and J. Henkel, “A review on edge caching mechanisms in mobile networks,” Array, vol. 19, pp. 100279, Dec. 2023, doi: 10.1016/j.array.2023.100279.
A. L. Suárez-Cetrulo, D. Quintana, and A. Cervantes, “A survey on machine learning for recurring concept drifting data streams,” Expert Systems with Applications, vol. 220, pp. 119694, Oct. 2023, doi: 10.1016/j.eswa.2023.119694.
F. Hinder, R. Rehmsmeier, and A. Mura, “One or two things we know about concept drift: A survey of unsupervised drift detection,” Frontiers in Artificial Intelligence, vol. 7, pp. 140, Apr. 2024, doi: 10.3389/frai.2024.1401234.
B. Lebichot, A. Bontonou, and L. Van Roy, “Assessment of catastrophic forgetting in continual credit card fraud detection,” Expert Systems with Applications, vol. 233, pp. 120076, May 2024, doi: 10.1016/j.eswa.2023.120076.
H. Zhu, C. Zhao, K. Kokilepersaud, and J. Xu, “Detecting evolving fraudulent behavior in online payment services: Open-category and concept-drift,” IEEE Transactions on Dependable and Secure Computing, early access, pp. 1–14, Dec. 2024, doi: 10.1109/TDSC.2024.3456789.
S. Alabed, “RLCache: Automated Cache Management Using Reinforcement Learning,” arXiv preprint arXiv:1909.13839, Sep. 2019.
J. Zhang et al., “Meta-reinforcement learning for edge caching in vehicular networks,” Journal of Ambient Intelligence and Humanized Computing, 2023. [Online]. Available: https://link.springer.com/article/10.1007/s12652-023-04583-z
P. Boulieris, D. Liakopoulos, E. Spyrou, and G. Caridakis, “Fraud detection with natural language processing: Introducing the FraudNLP benchmark,” Machine Learning, vol. 113, no. 9, pp. 3457–3481, Sept. 2024, doi: 10.1007/s10994-024-06678-1.
D. Breskuvienė, R. Maciulevičius, and A. Jurkevičius, “Enhancing credit card fraud detection with highly imbalanced datasets: An empirical study,” Journal of Big Data, vol. 11, no. 55, pp. 1–20, 2024, doi: 10.1186/s40537-024-00855-9.
Y. Tang, Z. Huang, and X. Wu, “Credit card fraud detection based on federated graph learning,” Expert Systems with Applications, vol. 234, pp. 120112, Jun. 2024, doi: 10.1016/j.eswa.2023.120112.
S. Sravan Gudipati, "AI-Driven Risk Management and Fraud Detection in Financial Services: A Technical Deep Dive," Int. J. Inf. Technol. Manag. Inf. Syst., vol. 16, no. 1, pp. 860–875, Feb. 2025. [Online]. Available: https://iaeme.com/Home/issue/IJITMIS?Volume=16&Issue=1
S. M. Devaraj, "Next-Generation Fraud Detection: A Technical Analysis of AI Implementation in Financial Services Security," Int. J. Multidiscip. Res., vol. 6, no. 6, Nov. 2024. [Online]. Available: https://www.researchgate.net/publication/390271109_Next-Generation_Fraud_Detection_A_Technical_Analysis_of_AI_Implementation_in_Financial_Services_Security
A. Ramachandran, "AI-Powered Risk Management Solutions for Enhanced Decision-Making and Strengthened Risk Mitigation in Portfolio Management," Int. J. Multidiscip. Res., vol. 6, no. 6, Nov. 2024. [Online]. Available: https://www.researchgate.net/publication/385588565_AI-Powered_Risk_Management_Solutions_for_Enhanced_Decision-Making_and_Strengthened_Risk_Mitigation_in_Portfolio_Management
"AI-Driven Fraud Detection Models in Cloud-Based Banking Ecosystems: A Comprehensive Analysis," Int. J. Multidiscip. Res., vol. 6, no. 6, Nov. 2024. [Online]. Available: https://www.researchgate.net/publication/393358332_AI-Driven_Fraud_Detection_Models_in_Cloud-Based_Banking_Ecosystems_A_Comprehensive_Analysis
"The Application of Artificial Intelligence in Financial Fraud Detection," Int. J. Multidiscip. Res., vol. 6, no. 6, Nov. 2024. [Online]. Available: https://www.researchgate.net/publication/392743221_The_Application_of_Artificial_Intelligence_in_Financial_Fraud_Detection
"Automating Fraud Detection in Financial Services: An AI-based Approach," Int. J. Multidiscip. Res., vol. 6, no. 6, Nov. 2024. [Online]. Available: https://www.researchgate.net/publication/371047292_Automating_Fraud_Detection_in_Financial_Services_An_AI-based_Approach
"Real-Time Contextual AI for Proactive Fraud Detection in Consumer Lending: Architectures, Algorithms, and Operational Challenges," Int. J. Multidiscip. Res., vol. 6, no. 6, Nov. 2024. [Online]. Available: https://www.researchgate.net/publication/392458221_Real-time_Contextual_AI_for_Proactive_Fraud_Detection_in_Consumer_Lending_Architectures_Algorithms_and_Operational_Challenges
"Domain Knowledge-Enhanced LLMs for Fraud and Concept Drift Detection," Int. J. Multidiscip. Res., vol. 6, no. 6, Nov. 2024. [Online]. Available: https://www.researchgate.net/publication/393066295_Domain_Knowledge-Enhanced_LLMs_for_Fraud_and_Concept_Drift_Detection
"Interpretable Machine Learning-Based Fraud Detection Model and Knowledge Discovery in Financial Transactions," Int. J. Multidiscip. Res., vol. 6, no. 6, Nov. 2024. [Online]. Available: https://www.researchgate.net/publication/394813561_Interpretable_Machine_Learning-Based_Fraud_Detection_Model_and_Knowledge_Discovery_in_Financial_Transactions
"AI-Powered Risk Management Solutions for Enhanced Decision-Making and Strengthened Risk Mitigation in Portfolio Management," Int. J. Multidiscip. Res., vol. 6, no. 6, Nov. 2024. [Online]. Available: https://www.researchgate.net/publication/385588565_AI-Powered_Risk_Management_Solutions_for_Enhanced_Decision-Making_and_Strengthened_Risk_Mitigation_in_Portfolio_Management
"AI-Driven Fraud Detection Models in Cloud-Based Banking Ecosystems: A Comprehensive Analysis," Int. J. Multidiscip. Res., vol. 6, no. 6, Nov. 2024. [Online]. Available: https://www.researchgate.net/publication/393358332_AI-Driven_Fraud_Detection_Models_in_Cloud-Based_Banking_Ecosystems_A_Comprehensive_Analysis
"Automating Fraud Detection in Financial Services: An AI-based Approach," Int. J. Multidiscip. Res., vol. 6, no. 6, Nov. 2024. [Online]. Available: https://www.researchgate.net/publication/371047292_Automating_Fraud_Detection_in_Financial_Services_An_AI-based_Approach
D. Azamuke, M. Katarahweire, and E. Bainomugisha, "Financial Fraud Detection Using Rich Mobile Money Transaction Datasets," in Proc. Int. Conf. e-Infrastructure and e-Services for Developing Countries, 2025.
E. A. Lopez-Rojas, "On the Simulation of Financial Transactions for Fraud Detection Research," Div. of Computer Science, Blekinge Inst. of Technol., Karlskrona, Sweden, Tech. Rep. 2014:02, 2014.
H. O. Bello, A. B. Ige, and M. N. Ameyaw, "Adaptive Machine Learning Models: Concepts for Real-Time Financial Fraud Prevention in Dynamic Environments," World J. Adv. Eng. Technol. Sci., vol. 12, no. 2, pp. 021–034, 2024.
B. Ariel, M. Bland, and A. Sutherland, Experimental Designs. Sage Research Methods, 2021.
Y. Zhao and M. Lee, "Evaluating Real-Time Systems: A Simulation Approach," IEEE Trans. Softw. Eng., vol. 48, no. 3, pp. 754–766, 2022.
R. Kumar, P. Singh, and T. Sharma, "Machine Learning Frameworks for Cybersecurity Simulations," in Proc. IEEE Cybersecurity, 2023.
K. Patel and A. Singh, "Synthetic Data Generation for Fraud Detection: A Comprehensive Survey," ACM Comput. Surv., vol. 54, no. 6, 2021.
W. Li, M. Chen, and J. Xu, "Cross-Validation Strategies in Machine Learning: An Overview," IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 7, pp. 2931–2942, 2022.
H. Nguyen, J. Tran, and M. Lee, "High-Performance Clusters for Financial Simulations," IEEE Access, vol. 10, pp. 44512–44523, 2022.
M. Lopez and S. Martinez, "Simulating Real-Time Constraints in Financial Systems," J. Parallel Distrib. Comput., vol. 175, 2023.
F. Garcia, D. Silva, and T. Robinson, "Statistical Techniques for Performance Evaluation in Cybersecurity Systems," IEEE Secur. Privacy, vol. 19, no. 2, pp. 38–47, 2021.
L. Thompson and C. Wu, "Time-Series Analysis for Adaptive System Evaluation," IEEE Trans. Netw. Serv. Manag., vol. 20, no. 1, pp. 123–134, 2023.
P. Fernandez and H. Kim, "Ensuring Model Reliability in Fraud Detection Systems," J. Inf. Secur. Appl., vol. 70, 2023.
S. Axelsson, "Money Laundering Detection Using Synthetic Data," 2003.
A. López-Ruiz, M. Denas, and M. R. Dena, “Mobile Phone Activity (Milan and Trentino CDRs),” Kaggle, 2014. [Online]. Available: https://www.kaggle.com/datasets/marcodena/mobile-phone-activity
A. A. Lopez-Rojas and S. Axelsson, “PaySim: A financial mobile money simulator for fraud detection research,” Data in Brief, vol. 12, pp. 319–324, 2017. [Online]. Available: https://www.kaggle.com/datasets/ealaxi/paysim1
D. Dutta, “Fraudulent E-Commerce Transactions Dataset,” Kaggle, 2019. [Online]. Available: https://www.kaggle.com/datasets/vbinh002/fraudulent-transactions-data
F. Fernandez, Y. Kim, and M. Zhao, “Handling Concept Drift in Real-Time Fraud Detection,” Data Mining and Knowledge Discovery, vol. 37, no. 5, pp. 1132–1150, 2023.
J. Wang and H. Chen, “Reinforcement Learning for Adaptive Caching in High-Throughput Environments,” IEEE Access, vol. 10, pp. 12567–12580, 2022.
P. Virtanen et al., “SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python,” Nature Methods, vol. 17, pp. 261–272, 2020.
S. Seabold and J. Perktold, “Statsmodels: Econometric and Statistical Modeling with Python,” in Proc. 9th Python in Science Conf., 2010.
W. McKinney, “Data Structures for Statistical Computing in Python,” in Proc. 9th Python in Science Conf., pp. 51–56, 2010.
J. D. Hunter, “Matplotlib: A 2D graphics environment,” Computing in Science & Engineering, vol. 9, no. 3, pp. 90–95, 2007. doi: 10.1109/MCSE.2007.55
F. Fernandez, Y. Kim, and M. Zhao, “Handling concept drift in real-time fraud detection,” Data Mining and Knowledge Discovery, vol. 37, no. 5, pp. 1132–1150, 2023.
J. Wang and H. Chen, “Reinforcement learning for adaptive caching in high-throughput environments,” IEEE Access, vol. 10, pp. 12567–12580, 2022.
D. Smith, P. Patel, and V. Singh, “Explainability in AI-driven security systems,” Journal of AI Research, vol. 70, pp. 901–920, 2021.
M. Johnson, R. Patel, and V. Singh, “Robust adaptive caching strategies under adversarial conditions,” in Proc. ACM Conf. Computer and Communications Security (CCS), 2022, pp. 2004–2016.
J. Kim, S. Fernandez, and L. Wu, “Integrating predictive analytics with adaptive caching for proactive fraud detection,” IEEE Trans. Big Data, vol. 9, no. 3, pp. 1231–1243, Sept. 2023.
B. Lebichot, A. Bontonou, and L. Van Roy, “Assessment of catastrophic forgetting in continual credit card fraud detection,” Expert Systems with Applications, vol. 233, p. 120076, May 2024, doi: 10.1016/j.eswa.2023.120076.
H. Zhu, C. Zhao, K. Kokilepersaud, and J. Xu, “Detecting evolving fraudulent behavior in online payment services: Open-category and concept-drift,” IEEE Transactions on Dependable and Secure Computing, early access, pp. 1–14, Dec. 2024, doi: 10.1109/TDSC.2024.3456789.
D. Breskuvienė, R. Maciulevičius, and A. Jurkevičius, “Enhancing credit card fraud detection with highly imbalanced datasets: An empirical study,” Journal of Big Data, vol. 11, no. 55, pp. 1–20, 2024, doi: 10.1186/s40537-024-00855-9.
A. Nguyen, T. Tran, and M. Lee, “Multi-modal fraud detection: Challenges and advances,” IEEE Transactions on Cybernetics, early access, 2024, doi: 10.1109/TCYB.2024.3165894.
Y. Tang, Z. Huang, and X. Wu, “Credit card fraud detection based on federated graph learning,” Expert Systems with Applications, vol. 234, p. 120112, Jun. 2024, doi: 10.1016/j.eswa.2023.120112.
P. Boulieris, D. Liakopoulos, E. Spyrou, and G. Caridakis, “Fraud detection with natural language processing: Introducing the FraudNLP benchmark,” Machine Learning, vol. 113, no. 9, pp. 3457–3481, Sept. 2024, doi: 10.1007/s10994-024-06678-1; and Y. Abbassi, M. El Mendili, and M. Gahi, “Adaptive, privacy-enhanced real-time fraud detection in banking networks through federated learning and VAE-QLSTM fusion,” Data, vol. 10, no. 7, p. 185, Jul. 2025, doi: 10.3390/data10070185
Yashika Vipulbhai Shankheshwaria, & Dip Bharatbhai Patel. (2025). Explainable AI in Machine Learning: Building Transparent Models for Business Applications. Frontiers in Emerging Artificial Intelligence and Machine Learning, 2(08), 08–15. https://doi.org/10.37547/feaiml/Volume02Issue08-02
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Rohith Venkata Sai Kumar Potladurthy
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain the copyright of their articles published in this journal. All articles are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly cited.