Proceedings of the First International Conference on Science, Engineering and Technology Practices for Sustainable Development, ICSETPSD 2023, 17th-18th November 2023, Coimbatore, Tamilnadu, India

Research Article

Exploration on Financial Risk Management under Machine Learning Algorithms

Download42 downloads
  • @INPROCEEDINGS{10.4108/eai.17-11-2023.2342821,
        author={Yimei  Cao and Di  Zhao and Chaoying  Xiao},
        title={Exploration on Financial Risk Management under Machine Learning Algorithms},
        proceedings={Proceedings of the First International Conference on Science, Engineering and Technology Practices for Sustainable Development, ICSETPSD 2023, 17th-18th November 2023, Coimbatore, Tamilnadu, India},
        publisher={EAI},
        proceedings_a={ICSETPSD},
        year={2024},
        month={1},
        keywords={machine learning algorithms financial risks random forests principal component analysis risk warning},
        doi={10.4108/eai.17-11-2023.2342821}
    }
    
  • Yimei Cao
    Di Zhao
    Chaoying Xiao
    Year: 2024
    Exploration on Financial Risk Management under Machine Learning Algorithms
    ICSETPSD
    EAI
    DOI: 10.4108/eai.17-11-2023.2342821
Yimei Cao1,*, Di Zhao1, Chaoying Xiao1
  • 1: School of Economics and Management, Shaanxi Fashion Engineering University, Xi’an 712046, Shaanxi, China
*Contact email: emay_cao@163.com

Abstract

Financial crises have a cyclical nature. In the context of economic globalization and the new normal, trade, industry, financial markets, capital markets, foreign exchange markets, real estate, etc., among countries have become interconnected through multiple channels. At the same time, it also leads to a very complex transmission chain of financial crises. If a financial crisis occurs, it would have a significant negative impact on the country, society, and people's lives. On the basis of establishing a system of financial risk warning indicators, this article used principal component analysis to reduce the dimensionality of the selected economic and financial index data. The main factors affecting the system's financial risk were extracted, and the comprehensive indicator values obtained through K-means clustering analysis were used to divide the risk level, thereby determining whether the risk warning state has been reached. In the statistical results of financial risk using the random forest method, the probability of financial risk in 2019 was 19%; the probability of financial risk in 2020 was 8%, and the probability of financial risk in 2021 was 5%. By strengthening the identification and prevention of financial risks, this article can provide a more comprehensive and accurate monitoring and evaluation of financial risks.