Analysis of Internet Financial Risks Based on Deep Learning and BP Neural Network

Article


Liu, Zixian, Du, Guansan, Zhou, Shuai, Lu, Haifeng and Ji, Han. 2022. "Analysis of Internet Financial Risks Based on Deep Learning and BP Neural Network." Computational Economics. 59 (4), pp. 1481-1499. https://doi.org/10.1007/s10614-021-10229-z
Article Title

Analysis of Internet Financial Risks Based on Deep Learning and BP Neural Network

ERA Journal ID18157
Article CategoryArticle
AuthorsLiu, Zixian, Du, Guansan, Zhou, Shuai, Lu, Haifeng and Ji, Han
Journal TitleComputational Economics
Journal Citation59 (4), pp. 1481-1499
Number of Pages19
Year2022
PublisherSpringer
Place of PublicationUnited States
ISSN0927-7099
1572-9974
Digital Object Identifier (DOI)https://doi.org/10.1007/s10614-021-10229-z
Web Address (URL)https://link.springer.com/article/10.1007/s10614-021-10229-z
Abstract

The study aims to analyze and forecast Internet financial risks based on the model based on deep learning and the Back Propagation Neural Network (BPNN). First, the theory of Internet financial risks is introduced and a theoretical framework for analyzing and forecasting internet financial risks is established. Second, the theory of the BPNN and the algorithms based on deep learning are introduced. Then, the model based on the BPNN and deep learning is implemented to improve the early warning of Internet financial risks, analyze the data image of China's Gross Domestic Product (GDP), currency (M2), non-performing loan records, and the Shanghai Composite Index from 2006 to 2020, and forecast the risks in 2021. Through the model based on deep learning and BPNN, it can be found that the trends of the growth rate of China's GDP take on the shapes of V and L, and the trend of M2 is opposite to that of GDP. In the whole year, there is a low at the beginning and the end of the year, and the monthly non-performing loans and the Shanghai Composite Index decrease. The forecast made by the model is that there will be many fluctuations in 2021. At present, China’s economy just enters the era of the new normal, which helps to build a more scientific and sensitive early warning system for financial risks. The model based on the BPNN and deep learning greatly improves the timeliness of forecasts and has a positive impact on the stability of China’s financial environment.

KeywordsBP neural network ; Early warning; Financial risks ; GDP growth rate; Deep learning
Related Output
Is supplemented byCorrection to: Analysis of Internet Financial Risks Based on Deep Learning and BP Neural Network
ANZSRC Field of Research 20203899. Other economics
Public Notes

File reproduced in accordance with the copyright policy of the publisher/author.

This article has been corrected. Please see the Related Output.

Byline AffiliationsLiaoning University, China
People’s Bank of China, China
Faculty of Business, Education, Law and Arts
Permalink -

https://research.usq.edu.au/item/z0257/analysis-of-internet-financial-risks-based-on-deep-learning-and-bp-neural-network

Download files


Published Version
s10614-021-10229-z.pdf
File access level: Anyone

  • 33
    total views
  • 58
    total downloads
  • 2
    views this month
  • 2
    downloads this month

Export as

Related outputs

Correction to: Analysis of Internet Financial Risks Based on Deep Learning and BP Neural Network
Liu, Zixian, Du, Guansan, Zhou, Shuai, Lu, Haifeng and Ji, Han. 2024. "Correction to: Analysis of Internet Financial Risks Based on Deep Learning and BP Neural Network ." Computational Economics. https://doi.org/10.1007/s10614-024-10600-w
Application of innovative risk early warning mode under big data technology in Internet credit financial risk assessment
Du, Guansan, Liu, Zixian and Lu, Haifeng. 2021. "Application of innovative risk early warning mode under big data technology in Internet credit financial risk assessment ." Journal of Computational and Applied Mathematics. 386. https://doi.org/10.1016/j.cam.2020.113260