Research On Credit Rating Of Automobile Dealers Based On Data Mining

the development of China's economy has entered the new normal,China's car sales growth has slowed down.As an important channel of automobile sales,automobile dealers are generally faced with problems such as capital shortage and turnover difficulties.In order to alleviate the economic pressure of dealers,auto companies will grant appropriate credit line to dealers according to their operating conditions.However,in the process of mutual cooperation between dealers and auto companies,there are still problems such as lack of credit.Some dealers with poor credit make auto companies bear risks.Therefore,credit rating of dealers can help improve the credit level of dealers,so that the cooperation between dealers and automobile enterprises will be closer,and the market competitiveness will be correspondingly improved.On the basis of expounding the domestic and foreign research trends of credit evaluation,this paper analyzes and studies the subjective factors and rating models in the index evaluation system from the perspective of automobile manufacturers,taking automobile dealers as the research object.Finally,the validity and reliability of the model are proved by concrete cases in combination with school-enterprise cooperation projects.The specific research content is as follows:(1)according to the existing credit index system and combining with the characteristics of dealers,this paper constructs a set of credit rating system suitable for automobile enterprises to credit dealers.Firstly,based on the analysis and discussion of the existing credit rating index system,the credit rating index system of automobile dealers is constructed based on the existing sample data.Then,the subjective data in the system,such as the customer satisfaction index,is acquired through the web crawler technology,and the text data mining is carried out.The qualitative subjective data is transformed into more intuitive quantitative data through the viewpoint orientation analysis of the comment data.In addition,the preprocessing method and process of the sample data in the system are studied,which lays a foundation for the establishment of the credit rating model.(2)this paper uses fuzzy neural network algorithm to score the credit of dealers.Based on the study of fuzzy neural network theory and modeling process,the credit model is simulated and optimized by combining the credit rating system and sample data.Compared with the traditional BP neural network,its mean square error is 31.1% lower than that of BP neural network,and it has better generalization ability.(3)combining the status quo and demand analysis of school-enterprise cooperation projects,this paper optimizes and designs the informatization management of the credit rating model of automobile dealers by using the research result of enterprise informatization of the project team – yiku intelligent collaborative software development platform.The optimized platform can connect dealers to manage them and generate linkage effect when credit risk occurs.The research of this paper has realized an effective combination with practical application.