The Application Of Data Mining In Personal Credit Risk Controlling And Forecasting

In recent years, with the constant development of the market economy in our country, incomes and the level of consumption of both rural and urban residents have increased steadily. Many bank institutions have made consume loan market a strategic priority. Consume loan market grows very quickly. They need personal credit analysis methods and analysis systems urgently. But many banks use expert system to evaluate credit risk. And there are many personal subjective factors in the method. So it is of very obvious practical significance and high value of research to apply data mining technique to the field of personal credit analysis to prevent from credit risk, to choose scientific models and establish a system in order to assist the assessor in their work. In the dissertation, Firstly, we put forward an ideal that credit risk is separated into different class according to the probability of people's breach. And then we use decision tree, neural network, clustering to analyze a large amount of personal credit data and build a credit risk evaluation model. Based on the model, probability of people's breach can be calculated accurately. At the same time we provide an overview of the application of data mining in the credit risk and summarizing the advantage and disadvantage of different methods of data mining. This paper focuses on how to use data mining to control and forecast the credit risk. Specifically, there are three major contend in this paper.Firstly, we put forward that personal credit risk is determined by probability of people's breach. And then we build the rule of separating credit rating and a set of indexed to analyze credit riskSecondly, we build a high accuracy credit risk analyzing model. In this paper, we use decision tree, neural network, clustering technology to analyze data and get a high accuracy model.