文献类型： 会议论文

第一作者： Jin Wang

作者： Jin Wang ¹ ; Zhen Tang ² ;

作者机构： 1.Sinounited Investment Group Corporation LIMITED, POSTDOCTORAL PROGRAMME, Beijing, P.R. CHINA

2.Agricultural Bank of China, SuZhou, P.R. CHINA

关键词： Technological innovation;Machine learning algorithms;Computational modeling;Neural networks;Machine learning;Predictive models;Prediction algorithms

会议名称： International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology

主办单位：

页码： 114-119

摘要： With the continuous development of computer technology, artificial intelligence has penetrated into various fields and guided corresponding innovations. This also leads to increasing competition in various fields, requiring corresponding participants to engage in technological innovation. In this context, machine learning tools are often used to mine data in order to obtain the hidden patterns behind a large amount of complex data. BP neural network, as an important machine learning tool, has been used by many scholars for related research. In the field of enterprise financial risk research, BP neural networks can also be used for financial risk warning. Therefore, this paper focuses on the application of BP neural network in enterprise financial crisis warning. In the research, this paper constructs a financial crisis warning model based on the K-means clustering and BP neural network, and achieved good warning effects. To further improve the early warning effect of the model, this paper further introduces genetic algorithm to optimize the BP neural network, and constructs a hybrid model of GA-K-means-BP neural network to predict enterprise financial crises. Meanwhile, based on the hybrid model, the research shows that the early warning effect can be improved by introducing new enterprise characteristic indicators.

分类号： tp3-53