Research On Data Mining Bases On Business Intelligence

For wining initiative and more commercial opportunity in furious market, business intelligence is needed to guidance business behavior and to assist decision-making. Data mining is a very useful method, which uses of decision tree, association rule, classification and clustering technology to make decision. Clustering is data mining technology which processes data analysis under the absence of prior knowledge and guidance. Traditional clustering analysis is a hard division. The boundary of division is very clear. However, practically, the majority of the objects do not have strict properties. There are lots of interaction between form and attribute of species. Therefore, the soft division is more suitable than hard one, we call it fuzzy clustering analysis.In order to solve the problem of credit risk in commercial bank, I use fuzzy clustering, which bases on the using of fuzzy equivalence relations, to analyze the credit risk in banks. The system I built can find out the key factors which decided the possibility of Payment default in advance, system processes these factors which is collected and given weight to be a quantitative score, A new fuzzy clustering score model will be built according to process of the quantitative score .The keystone in this paper: first, Fuzzy clustering score model improves the traditional credit scoring methods in many fields. Such as the traditional one can not reflect the dynamic process of changes in factors insufficiently. Moreover, the traditional method is not good at reflecting the restriction and relationship between each factor. Fuzzy clustering score model is a behavior score grading model, that means it has fuctions of controlling credit recollecting fund and estimating business risk in advance. This paper plays a promotive role on the bank's credit policy-making scientifically and professionally. Second, Results of Data mining is visualization. I realize the fuction through graphics and text to display knowledge obviously, which will help users to understand.