Building up Default Predicting Model based on Logistic Model and Misclassification Loss

Nowadays, there are gaps between default predicting models and real life, such as: a) ratio of number of default enterprises to the number of normal enterprises in the enterprise's short-term loan default predicting model differs vastly from the practical ratio; b) there are few studies considering the misclassification loss; c) as well as few studies considering the qualitative indexing, such as scale, region, and industry. To solve the aforementioned problems, applying stepwise logistic regression model, a default predicting model considering the misclassification loss is built, abandoning the pairwise pattern and using all samples, and introducing qualitative indexes. The model is significant because of statistical testing. It is more practical and the classification rates are also better.