Bank Credit Scoring System Based On Data Mining Research

Nowadays the society is full of all kinds of information . It becomes more and more important to make the best use of the information .As a result , more and more people focus on data mining , as a newly-established frontier subject and the most active field in the research of information system and computer science.Credit risk is one of the oldest and the most important form of risk in financial market . It is an important problem that the economic entities (especially financial institutions), investors and consumers are facing in modern society. It directly affects all kinds of activities in modern economic life ,macroscopical decision and economic development of a country .It even affects steady development of the whole world economic .Credit risk management has a long history in abroad , and the measure of credit risk gradually transform from static data analysis to quantitative analysis , the decision of credit risk begins to adopt the method of credit model . In our country , credit risk management is just on the beginning and it is lack of system research .According to some related agreements of WTO ,limitation on foreign currency business ,national currency business ,business permission card and so on for foreign capital banks will be cancelled gradually in our country after China join in WTO .But in China , the ratio of bad loans in most of banks are higher than 10%(the international alertness line)and 15%(the regulatory standard of our country). It has important meaning to quicken the research of credit risk management in our country and to build credit rating model fitting in with Chinese situation for enterprise and individual as soon as possible . The model can supply the foundation of the scientific management and correct decision for financial institutions and improve their competitive ability in the world . On the basis of deeply researching on data mining technology , feedforward neural net work , decision tree and credit management for individual and beginning with quantitative analysis of credit risk management , this thesis builds a credit rating model based on BP neural network for individual aiming at the fact of credit risk management in our country .The...