Application of Large Models in the Financial Field

DOI

10.2991/978-94-6463-702-1_53How to use a DOI?

Keywords

Large Model; Artificial Intelligent; Financial Industry; Landing Scene

Abstract

This article discusses the application status, challenges and future prospects of large models in financial field. Large model, as a deep learning model with many parameters, has already achieved remarkable results in many areas like speech recognition, image processing and natural language processing and starts to be applied in many scenarios such as investment, risk control and insurance in the financial industry. This article first introduces the current application status of financial large models, including model application, model direction innovation, cooperation and coexistence. Then, taking Ping An Bank as an example, the specific application of large models in financial scenarios is analyzed in detail, including model introduction, structure and application cases. Additionally, the article also discusses the SWOT analysis of large models in the financial field, analyzing its strengths, weaknesses, opportunities and threats. In the case of Ping An Bank, this article introduces the structural framework of the Ping An Bank GPT large model to explain how the large model can be used in scenarios such as intelligent early warning, analysis and monitoring, and its role in improving the efficiency of risk control personnel, risk early warning capabilities and response potential for fraud capabilities. However, large model also have to face the challenges in the financial field, such as lacking of professional data, high training costs and the black box effect [1] of the model. The outlook part of the article points out that the application of large models and artificial intelligence in the financial industry is a general trend, and the growth in market size also proves this. Financial institutions and technology service providers need to ensure the credibility of the data used for algorithm training and build a reasonable data processing environment. At the same time, financial institutions can prioritize lower-risk projects for trial and error to improve the data and algorithms of large models. Last, the article provides resources for further reading through references, covering multiple applications and challenges of large models in finance, and how these challenges can be addressed through technical and regulatory measures.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jiayi Liang
PY  - 2025
DA  - 2025/05/05
TI  - Application of Large Models in the Financial Field
BT  - Proceedings of the 2025 10th International Conference on Financial Innovation and Economic Development (ICFIED 2025)
PB  - Atlantis Press
SP  - 505
EP  - 513
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-702-1_53
DO  - 10.2991/978-94-6463-702-1_53
ID  - Liang2025
ER  -