International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Edge AI for Real-Time Fraud Detection on Resource-Constrained Devices Using Lightweight Machine Learning Models |
|---|---|
| ABSTRACT | The exponential growth of digital payment systems, mobile banking, and e-commerce has made financial fraud a critical global concern, with estimated annual losses exceeding $32 billion. Traditional fraud detection systems depend on cloud-hosted deep learning models that suffer from high inference latency, continuous bandwidth consumption, and significant privacy vulnerabilities arising from transmitting sensitive transactional data over networks. This paper proposes FraudEdge, a novel lightweight machine learning framework designed for real-time fraud detection directly on resource-constrained edge devices such as smartphones and IoT payment terminals. FraudEdge combines a quantised and pruned Gradient Boosting classifier with an on-device anomaly scoring pipeline, achieving 98.6% detection accuracy and a false positive rate of only 1.2% on the IEEE-CIS and PaySim benchmark datasets. The optimised model occupies just 340 KB of flash memory and performs inference in under 8 ms with 92 mW average power draw on an ARM Cortex-M4 microcontroller. Experimental comparisons against cloud-based XGBoost, deep neural network baselines, and existing lightweight models demonstrate that FraudEdge consistently outperforms competitors on the combined accuracy–latency–privacy axis, validating its suitability for production-grade edge deployment without any reliance on cloud connectivity. |
| AUTHOR | PROF. MANJULA P, RIFFATH AMANI, SINCHANA S N, SUPRIYA M, TOUFIYA BANU Assistant Professor, Dept. of CS&E., Jain Institute of Technology, Davangere, Karnataka, India UG Student, Dept. of CS&E, Jain Institute of Technology, Davangere, Karnataka, India |
| VOLUME | 184 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1405013 |
| pdf/13_Edge AI for Real-Time Fraud Detection on Resource-Constrained Devices Using Lightweight Machine Learning Models.pdf | |
| KEYWORDS | |
| References | [1] The Nilson Report, "Card Fraud Losses Worldwide," Issue 1232, March 2023. [2] W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, "Edge Computing: Vision and Challenges," IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637–646, 2016. [3] S. Bhattacharyya, S. Jha, K. Tharakunnel, and J. C. Westland, "Data Mining for Credit Card Fraud: A Comparative Study," Decision Support Systems, vol. 50, no. 3, pp. 602–613, 2011. [4] A. Dal Pozzolo, O. Caelen, R. A. Johnson, and G. Bontempi, "Calibrating Probability with Undersampling for Unbalanced Classification," in Proc. IEEE SSCI, pp. 1–8, 2015. [5] T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System," in Proc. ACM KDD, pp. 785–794, 2016. [6] S. Yao, G. Kou, Y. Peng, and X. Li, "BiLSTM for Temporal Pattern Recognition in Credit Card Fraud Detection," IEEE Access, vol. 9, pp. 31318–31328, 2021. [7] D. Wang, J. Lin, P. Cui, Q. Jia, Z. Wang, Y. Fang, Q. Yu, and W. Zhu, "A Semi-Supervised Graph Attentive Network for Financial Fraud Detection," in Proc. IEEE ICDM, pp. 598–607, 2019. [8] P. Warden and D. Situnayake, TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers. O’Reilly Media, 2019. [9] R. David, J. Duke, A. Jain, V. J. Reddi, N. Jeffries, J. Li, and N. Kreeger, "TensorFlow Lite Micro: Embedded Machine Learning for TinyML Systems," in Proc. MLSys, 2021. [10] H. Ouyang, S. Bhatt, and A. Subramanian, "Towards Real-Time Fraud Detection on Embedded Devices Using Compressed Machine Learning," in Proc. IEEE IoT-J Workshop, pp. 112–118, 2022. [11] Y. Liu, X. Fan, C. Chen, X. Zheng, C. Zhou, L. Li, and Z. Li, "Federated Learning for Credit Card Fraud Detection," IEEE Transactions on Computational Social Systems, vol. 8, no. 6, pp. 1371–1378, 2021. [12] G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T. Liu, "LightGBM: A Highly Efficient Gradient Boosting Decision Tree," in Proc. NeurIPS, pp. 3146–3154, 2017. [13] E. A. Lopez-Rojas, A. Elmir, and S. Axelsson, "PaySim: A Financial Mobile Money Simulator for Fraud Detection," in Proc. EMSS, pp. 249–255, 2016. |
