%0 Journal Article
%T 基于BP神经网络的农业企业信用风险测度模型研究<br>Research on Credit Risk Measurement Model of Agricultural Enterprises Based on BP Neural Network
%A 陈雨秋
%A 梁凯豪
%J Modern Management
%P 3033-3040
%@ 2160-732X
%D 2024
%I Hans Publishing
%R 10.12677/mm.2024.1412364
%X 随着近年来农业企业面临的复杂金融环境&#65292;如何测度农业企业的信用风险是成为了愈来愈重要的问题。本文旨在探索一种基于BP神经网络的农业企业信用风险测度模型&#65292;选取了2023年共316家财务数据健全且具有代表性的农业企业&#65292;选取了财务结构、偿债能力、盈利能力、运营效率四个一级大类指标的17个二级指标构建各农业企业信用风险评估指标体系。使用BP神经网络和SVM支持向量机进行二元回归&#65292;分别对比了XGBoost二元回归模型、分类树模型(DT)、朴素贝叶斯模型(NB)、随机森林(RF)回归模型。结果显示BP神经网络模型对于企业信用风险测度指标拥有更好的回归能力&#65292;且在性能和精度上优于其他模型。<br>With the increasingly complex financial environment faced by agricultural enterprises in recent years, measuring the credit risk of agricultural enterprises has become an increasingly important issue. This paper aims to explore a credit risk measurement model for agricultural enterprises based on BP neural networks. A total of 316 financially sound and representative agricultural enterprises&#8217; data from 2023 were selected, and a credit risk assessment index system for agricultural enterprises was constructed, consisting of 17 secondary indicators across four primary categories: financial structure, debt-paying ability, profitability, and operational efficiency. Binary regression was conducted using BP neural networks and SVM support vector machines, and compared with XGBoost binary regression model, Decision Tree (DT) model, Naive Bayes (NB) model, and Random Forest (RF) regression model. The results show that the BP neural network model has better regression capability for enterprise credit risk measurement indicators and outperforms other models in terms of performance and accuracy.
%K 农业信用风险&#65292
%K BP神经网络&#65292
%K 二元回归<br>Agricultural Credit Risk
%K BP Neural Network
%K Binary Regression
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=102611