基于深度置信网络的上市公司信用风险预警模型  

Credit Risk Early Warning Model of Listed Companies Based on Deep Belief Network

作　　者：方达 张玥[1] 黄珍珍 FANG Da;ZHANG Yue;HUANG Zhenzhen(School of Mathematics and Finance,Anhui Polytechnic University,Wuhu241000,Anhui,China)

机构地区：[1]安徽工程大学数理与金融学院,安徽芜湖241000

出　　处：《安顺学院学报》2023年第3期94-99,共6页Journal of Anshun University

基　　金：国家自然科学基金青年项目“带有α-稳定OU噪音小干扰的随时过程的参数与非参数估计”(12101004)。

摘　　要：我国上市公司信用风险事件频发,一定程度上阻碍了金融体系的稳定发展,信用风险预警势在必行。本文借助深度置信网络,构建上市公司信用风险预警模型和预警指标体系,给出风险预警警戒值,并验证了预警模型的有效性。The frequent occurrence of credit risk events of listed companies in my country has hindered the stable development of the financial system to a certain extent,and credit risk early warning is imperative.With the help of the deep belief network,this paper constructs the credit risk early warning model and early warning index system of listed companies,gives the risk early warning warning value,and verifies the validity of the early warning model.

关 键 词：深度置信网络 预警模型 特征提取 信用风险 

分 类 号：F275[经济管理—企业管理]