Research On Application Of SVM To Individual Housing Loan Credit Risk Evaluation

With the development of housing marketing in our country, the scale of consumer housing loans of commercial bank is increasing rapidly. At the same time, an intense rise in loan risks of commercial bank is witnessed and the bad loan ratio in our country is obviously higher than that in the developed countries. Therefore, it's very important for commercial bank to solve the risk problem in the development of housing loans, as well as establish an effective risk prevention system. The paper is based on DW&MIS platform of China Construction Bank Dalian Branch. Research on individual housing loan credit risk evaluation in enterprise risk management module of DW&MIS platform and implement a credit risk evaluation system based on support vector machine.Data mining is a new technique which integrates techniques of database, artificial intelligence and statistic learning. It aims at extracting novel and useful knowledge from large volumes of data. Classification is used to predict unknown label by the classifier which is trained with experiential data. It is a basic problem in data mining.Support vector machine is a new method in data mining. It has excellent theory foundations, which are structure risk minimization, conditional optimization theory and kernel space theory. In order to solve a complicated classification task, the core idea is that SVM maps the vectors from input space to feature space in which a linear separating hyperplane is structured. SVM has the advantage of global optimization, simple structure and good generalization. Recently, SVM has been successfully applied to handwritten digit recognition, face detection and face recognition, text classification fields.Firstly, the paper introduces the application background, individual housing loan state and individual credit evaluation method. Bring forward an improved individual credit evaluation method.Secondly, the paper studies SVM theory and algorithm in depth. Research on Platt's sequential minimal optimization algorithm. Implement Keerthi's improved SMO algorithmand linear kernel, polynomial kernel, RBF kernel and sigmoid kernel support vector machines.Thirdly, individual housing loan credit risk evaluation prototype system based on SVM is designed and realized. Apply the system to individual housing loan credit risk evaluation of China Construction Bank Dalian Branch. Extract classification mining data from DW&MIS platform and preprocess data. Through prediction accuracy comparison of different models, the paper concludes that RBF model is suitable for practical application. And prove that the improved credit risk evaluation method is better than the old method.Finally, the paper summarizes the whole study work and makes further prospects to the work.