Using Advanced Machine Learning Techniques for Anomaly Detection in Financial Transactions
DOI:
https://doi.org/10.36676/dira.v12.i3.106Keywords:
Machine Learning, Anomaly Detection, Financial TransactionsAbstract
Financial transaction anomaly detection has become a critical component of financial security, especially in light of the growing complexity of fraudulent activity and the increasing digitalization of financial transactions. The application of cutting-edge machine learning techniques has great potential in this regard, since they may leverage algorithmic accuracy and processing capacity to detect abnormalities that can point to fraudulent activity. The purpose of this introduction is to explore the basics, evolution, significance, research gaps, and the need for this study.
References
i) Dhanawat, V., 2022. Anomaly Detection in Financial Transactions using Machine Learning and Blockchain Technology. International Journal of Business Management and Visuals, ISSN: 3006-2705, 5(1), pp.34-41.
ii) Henry de Frahan, M.T., Wimer, N.T., Yellapantula, S. and Grout, R.W., 2022. Deep reinforcement learning for dynamic control of fuel injection timing in multi-pulse compression ignition engines. International Journal of Engine Research, 23(9), pp.1503-1521.
iii) Jafarigol, E. and Trafalis, T.B., 2024. A distributed approach to meteorological predictions: addressing data imbalance in precipitation prediction models through federated learning and GANs. Computational Management Science, 21(1), p.22.
iv) Website: https://shap.readthedocs.io/en/latest/
v) Website: https://towardsdatascience.com/lime-explain-machine-learning-predictions-af8f18189bfe
vi) Zhang, M., 2019, April. Use density-based spatial clustering of applications with noise (DBSCAN) algorithm to identify galaxy cluster members. In IOP conference series: earth and environmental science (Vol. 252, No. 4, p. 042033). IOP Publishing.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Darpan International Research Analysis
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
