Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 04018 | |
Number of page(s) | 11 | |
Section | AI and Advanced Applications | |
DOI | https://doi.org/10.1051/itmconf/20257004018 | |
Published online | 23 January 2025 |
Evolution of machine learning in financial risk management: A survey
Actuarial Science, Department of Applied Probability and Statistics, 93117 University of California, Santa Barbara, United States
Corresponding author: 1k_lu@ucsb.edu
Financial risk management plays a crucial role in daily financial decision-making, aiming to mitigate risk and maximize profit. Given its reliance on data, financial risk management can greatly benefit from the application of machine learning tools. Over the years, we've observed a clear trend in the evolution of these applications, marked by increasing model complexity and a broader range of manageable tasks. This paper contributes to the field in three key dimensions: First, we provide a clear taxonomy of risks and an introduction to relevant machine learning methods to establish a foundation and identify the targeted issues. Next, we explore real-world data applications, discussing the pros and cons of three methods, from the earliest to the most recent. Finally, based on the observed results, we highlight current challenges and limitations and propose potential directions for improvement.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.