Bank Loan Strategy Based on Evaluation and Decision Model

Abstract

In real life, in the face of small and medium-sized enterprises lacking mortgage assets, banks usually provide loans to enterprises with strong strength and stable supply-demand relationship according to credit policies, transaction notes information of enterprises and influence of upstream and downstream enterprises, and can give preferential interest rate to enterprises with high reputation and small credit risk. In order to better meet the application of the model in real life, the enterprise loan mode is introduced, and the risk assessment of each loan mode is carried out according to the actual situation. Finally, the fuzzy neural network model is introduced. The enterprise loan mode and three secondary indicators are taken as the input of the fuzzy neural network. Finally, a three-level index: loan risk assessment is obtained. Using Python program to preprocess the data, the original indicators in the given materials are extracted as the first level indicators, and then on the basis of the first level indicators, the main factor analysis and other methods are used to analyze the characteristics and scoring of the second level indicators. Then, the entropy weight is established to obtain the higher-level index loan tendency, and the loan propensity and enterprise reputation are used as parameters to establish the decision-making Model, step by step to get the bank’s quota allocation, interest rate, and finally get the bank allocation plan. In order to supplement the unknown data, this paper uses the known information to forecast the whole process of the unknown quantity, and then uses the data to forecast. First of all, it forecasts whether the default occurs, adds the predicted value to the whole eigenvalue, then forecasts the reputation rating, and finally completes the reasonable supplement of location data. TOPSIS model, SPSS software simulation machine learning, Fisher discriminant analysis