Scholarlink

Abstract <p>In China, a major agricultural country, the agricultural economy plays a crucial role in the national economy. As a representative of the agricultural industry chain, agricultural listed companies not only bear the responsibility of support, but also face various financial risks such as market fluctuations, climate change, and policy adjustments. This research is based on agricultural listed companies on the Shanghai and Shenzhen A-shares from 2010 to 2023, taking into account both financial and non-financial indicators from three years ago. Principal Component Analysis (PCA) dimensionality reduction and oversampling techniques (SMOTE) were used to handle sample imbalance. Through the BP neural network model optimized by genetic algorithm, the financial risk of agricultural listed companies was successfully predicted, and the overall accuracy rate reached 94<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12202_2025_8207_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> <!--LobJMat2560030Song-m1--> </InlineEquation>. Compared with the original neural network, the optimized neural network had better performance. This research provides important decision support for agricultural enterprises and investors and establishes an empirical foundation for further optimization of financial risk warning models.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

The Application of Genetic Algorithm Optimized Neural Network in Financial Risk Early Warning Model of Agricultural Listed Companies

  • 期刊论文

  • 发表日期：

    2025年2月1日

查看全文
  • Yingying Song,
  • Monchaya Chiangpradit,
  • Kamon Budsaba,
  • Piyapatr Busababodhin

摘要

Abstract

In China, a major agricultural country, the agricultural economy plays a crucial role in the national economy. As a representative of the agricultural industry chain, agricultural listed companies not only bear the responsibility of support, but also face various financial risks such as market fluctuations, climate change, and policy adjustments. This research is based on agricultural listed companies on the Shanghai and Shenzhen A-shares from 2010 to 2023, taking into account both financial and non-financial indicators from three years ago. Principal Component Analysis (PCA) dimensionality reduction and oversampling techniques (SMOTE) were used to handle sample imbalance. Through the BP neural network model optimized by genetic algorithm, the financial risk of agricultural listed companies was successfully predicted, and the overall accuracy rate reached 94 \(\%\) . Compared with the original neural network, the optimized neural network had better performance. This research provides important decision support for agricultural enterprises and investors and establishes an empirical foundation for further optimization of financial risk warning models.