A Novel Imbalanced Data Classification Approach Based on Logistic Regression and Fisher Discriminant

摘要: We introduce an imbalanced data classification approach based on logistic regression significant discriminant and Fisher discriminant. First of all, a key indicators extraction model correlation analysis is derived to extract features for customer classification. Secondly, the basis linear weighted utilizing discriminant, scoring established. And then, rating where number all ratings follows normal distribution constructed. The performance proposed classical SVM method are evaluated in terms their ability correctly classify consumers as default or nondefault customer. Empirical results using 2157 customers financial engineering suggest that better than dealing with Moreover, our contributes locating qualified banks bond investors.