Girish Wali; Chetan Bulla

Suspicious Activity Detection Model in Bank Transactions Using Deep Learning with Fog Computing Infrastructure

PDF (857KB), PP.1-17

Views: 0 Downloads: 0

Author(s)

Girish Wali ^1,* Chetan Bulla ²

1. SVP - Business Architecture, IT Business Lead Analyst, Business Analysis & Product Solutions at CITI Bank, India

2. Professor of Computer Science and Engineering, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijieeb.2024.06.01

Received: 7 Feb. 2024 / Revised: 22 May 2024 / Accepted: 24 Jun. 2024 / Published: 8 Dec. 2024

Index Terms

Suspicious activity detection, Deep learning model, LSTM, Bio-inspired algorithms, Fog Computing, Google Colab

Abstract

The financial sector is grappling with significant challenges in detecting cyber attacks, leading to potential short- and long-term financial losses for banks and other institutions. The statistical and machine learning methods have been effective in identifying suspicious activities, they have struggled to achieve a balance between recall and precision. To improve accuracy, this paper introduces a novel approach that employs deep learning and bio-inspired algorithms to detect suspicious activities. The proposed model analyzes transactional patterns, quantities, and temporal aspects using a carefully curated dataset of labeled transactions. The model shows promising results in distinguishing between legitimate and fraudulent operations, achieving a balance between recall and precision. Further, many in the industry are transitioning to cloud computing infrastructures to enhance application performance. However, these infrastructures are not ideal for delay-sensitive applications, such as those in the medical and finance sectors. To address communication delays, fog computing has emerged as a new paradigm. The proposed model was simulated using Python and the Google Colab framework, and experimental results shows that improved accuracy and a balanced recall and precision.

Cite This Paper

Girish Wali, Chetan Bulla, "Suspicious Activity Detection Model in Bank Transactions Using Deep Learning with Fog Computing Infrastructure", International Journal of Information Engineering and Electronic Business(IJIEEB), Vol.16, No.6, pp. 1-17, 2024. DOI:10.5815/ijieeb.2024.06.01

Reference

[1]Santomero, A.M. (1999). Risk Management in Banking: Practice Reviewed and Questioned. In: Galai, D., Ruthenberg, D., Sarnat, M., Schreiber, B.Z. (eds) Risk Management and Regulation in Banking. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-5043-3_3
[2]Chetan M Bulla, Satish S Bhojannavar, Vishal M Danawade,"Cloud Computing: Research Activities and Challenges",Volume 2, Issue 5, International Journal of Emerging Trends & Technology in Computer Science (IJETTCS), 2013.
[3]Resul Das, Muhammad Muhammad Inuwa,"A review on fog computing: Issues, characteristics, challenges, and potential applications",vo. 10, Telematics and Informatics Reports,2023.https://doi.org/10.1016/j.teler.2023.100049.
[4]Shi, S., Tse, R., Luo, W. et al. Machine learning-driven credit risk: a systemic review. Neural Comput & Applic 34, 14327–14339 (2022). https://doi.org/10.1007/s00521-022-07472-2
[5]Leo, M., Sharma, S., & Maddulety, K. (2019, March 5). Machine Learning in Banking Risk Management: A Literature Review. Risks. https://doi.org/10.3390/risks7010029.
[6]Fang Dao, Yun Zeng, Jing Qian,"Fault diagnosis of hydro-turbine via the incorporation of bayesian algorithm optimized CNN-LSTM neural network",vol 290, Energy,Elsevier, 2024.
[7]Al‐Sawwa, Jamil, and Mohammad Almseidin. “A Spark-Based Artificial Bee Colony Algorithm for Unbalanced Large Data Classification.” Information, vol. 530, no. 11, 8 Nov. 2022, https://doi.org/10.3390/info13110530..
[8]Albatul Albattah & Murad A. Rassam. (2022) A Correlation-Based Anomaly Detection Model for Wireless Body Area Networks Using Convolution Long Short-Term Memory Neural Network. Sensors 22:5, pages 1951.
[9]Bulla, Chetan M., and Mahantesh N. Birje. "A Multi-Agent-Based Data Collection and Aggregation Model for Fog-Enabled Cloud Monitoring." IJCAC vol.11, no.1 2021: pp.73-92. http://doi.org/10.4018/IJCAC.2021010104
[10]Naghib, A., Jafari Navimipour, N., Hosseinzadeh, M. et al. A comprehensive and systematic literature review on the big data management techniques in the internet of things. Wireless Netw 29, 1085–1144 (2023). https://doi.org/10.1007/s11276-022-03177-5
[11]Pioli, L., Dorneles, C.F., de Macedo, D.D.J. et al. An overview of data reduction solutions at the edge of IoT systems: a systematic mapping of the literature. Computing 104, 1867–1889 (2022). https://doi.org/10.1007/s00607-022-01073-6
[12]Hongjian Li, Liangjie Liu, Xiaolin Duan, Hengyu Li, Peng Zheng, Libo Tang,"Energy-efficient offloading based on hybrid bio-inspired algorithm for edge–cloud integrated computation",vol 42,Sustainable Computing: Informatics and Systems,, elsevier, 2024.
[13]Sebin Jose, P. Victer Paul,"A survey on identification of influential users in social media networks using bio inspired algorithms,", Procedia Computer Science,Volume 218,2023.
[14]Bulla, C., Birje, M.N. (2022). Anomaly Detection in Industrial IoT Applications Using Deep Learning Approach. In: Fernandes, S.L., Sharma, T.K. (eds) Artificial Intelligence in Industrial Applications. Learning and Analytics in Intelligent Systems, vol 25. Springer, Cham. https://doi.org/10.1007/978-3-030-85383-9_9
[15]Aysha Shabbir, Maryam Shabir, Abdul Rehman Javed, Chinmay Chakraborty, Muhammad Rizwan, Suspicious transaction detection in banking cyber–physical systems, Computers & Electrical Engineering, Volume 97,2022,Elsevier
[16]A. Mahajan, V. S. Baghel and R. Jayaraman, "Credit Card Fraud Detection using Logistic Regression with Imbalanced Dataset," 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India, 2023, pp. 339-342.
[17]Michael J.A., Gordon S.L.Data Mining Technique for Marketing, Sales and Customer Support,John Wiley & Sons INC, New York (1997), p. 445
[18]Yi-Cheng Shih, Tian-Shyr Dai, Ying-Ping Chen, Yen-Wu Ti, Wun-Hao Wang, Yun Kuo, "Fund transfer fraud detection: Analyzing irregular transactions and customer relationships with self-attention and graph neural networks", Expert Systems with Applications,2024,https://doi.org/10.1016/j.eswa.2024.125211.
[19]Alghuried, A. A Model for Anomalies Detection in Internet of Things (IoT) Using Inverse Weight Clustering and Decision Tree., Technological University, Dublin, 2017.
[20]P. Zhang and Y. Liu, “Application of An Improved Artificial Bee Colony Algorithm,” IOP Conf. Ser.: Earth Environ. Sci., vol. 634, no. 1, p. 012056, Feb. 2021.
[21]Samir, A., Pahl, C.: Detecting and Predicting Anomalies for Edge Cluster Environments using Hidden Markov Models (HMM). In: 2019 Fourth IC-FMEC. pp. 21–28. IEEE, Rome, Italy (2019)
[22]Randhawa K., Loo C.H.U.K., Member S.,Credit card fraud detection using AdaBoost and majority voting, IEEE Access, 6 (2018), pp. 14277-14284, 10.1109/ACCESS.2018.2806420
[23]Guanjun L., Zhenchuan L., Lutao Z., Shuo W.,Random forest for credit card fraud. IEEE Access (2018)
[24]Aditi, Raut. (2023). Suspicious Activity Detection Using Machine Learning. International Journal For Science Technology And Engineering, 11(5):3745-3748. doi: 10.22214/ijraset.2023.52486.
[25]Wu, J., Yao, L., Liu, B., Ding, Z., Zhang, L.: Combining OC-SVMs With LSTM for Detecting Anomalies in Telemetry Data With Irregular Intervals. IEEE Access. 8, 106648–106659 (2020).
[26]Bulla, C., Birje, M.N. Improved data-driven root cause analysis in fog computing environment. J Reliable Intell Environ 8, 359–377 (2022).
[27]Demir, U., Ergen, S.C. ARIMA-based time variation model for beneath the chassis UWB channel. J Wireless Com Network 2016, 178 (2016). https://doi.org/10.1186/s13638-016-0676-3
[28]I. Ullah and Q. H. Mahmoud, "Design and Development of RNN Anomaly Detection Model for IoT Networks," in IEEE Access, vol. 10, pp. 62722-62750, 2022, doi: 10.1109/ACCESS.2022.3176317. keywords: {Internet of Things;Security;Deep learning;Intrusion detection;Computational modeling;Recurrent neural networks;Telecommunication traffic;Internet of Things;anomaly detection;recurrent neural network;convolutional neural network;LSTM;BiLSTM;GRU},
[29]Maya, S., Ueno, K., Nishikawa, T.: dLSTM: a new approach for anomaly detection using deep learning with delayed prediction. Int.Jou.of Dat.Sciee Ana. 8, 137–164 (2019).
[30]B. V. V, V. Indhuja, M. V. Reddy, N. Nikhitha and P. Pramila, "Suspicious Activity Detection using LRCN," 2023 5th International Conference on Smart Systems and Inventive Technology (ICSSIT), Tirunelveli, India, 2023, pp. 1463-1470, doi: 10.1109/ICSSIT55814.2023.10061045.
[31]Kamal, Upreti., Prashant, Vats., Aravindan, Srinivasan., K., V., Daya, Sagar., R, Mahaveerakannan., G., Charles, Babu. (2023). Detection of Banking Financial Frauds Using Hyper-Parameter Tuning of DL in Cloud Computing Environment. International Journal of Cooperative Information Systems, doi: 10.1142/s0218843023500247
[32]Talapula, D.K., Kumar, A., Ravulakollu, K.K., Kumar, M. (2023). Anomaly Detection in Online Data Streams Using Deep Belief Neural Networks. In: Swaroop, A., Kansal, V., Fortino, G., Hassanien, A.E. (eds) Proceedings of Fourth Doctoral Symposium on Computational Intelligence . DoSCI 2023. Lecture Notes in Networks and Systems, vol 726. Springer, Singapore. https://doi.org/10.1007/978-981-99-3716-5_59
[33]Torabi, H., Mirtaheri, S.L. & Greco, S. Practical autoencoder based anomaly detection by using vector reconstruction error. Cybersecurity 6, 1 (2023). https://doi.org/10.1186/s42400-022-00134-9
[34]Meenakshi, Ravindra S, Girish Wali, Chetan Bulla, Jitender Tanwar, Madhava Rao Chunduru, Surjeet, "AI Integrated Approach for Enhancing Linguistic Natural Language Processing (NLP) Models for Multilingual Sentiment Analysis",Vol. 23 issueNo. 1, Linguistic and Philosophical Investigations, (2024).
[35]Wali, G., Kori, A., Bulla, C., & AIML, K. Market Risk Assessment Using Deep Learning Model and Fog Computing Infrastructure.

International Journal of Information Engineering and Electronic Business (IJIEEB)