Replication Data for: default prediction of P2P loan based on improved stacking model

Data Sources: Training Set of Give me Some Credit Data in Kaggle Platform and a series of new data obtained after a series of pre-processing; Data format: three CSV copies; Data Description: The data set includes the age, income, family and loan situation of borrowers and there are 11 variables in total in which Serious Dlqin2yrs is lategory label,.1 represents default, 0 represents non-default, and another 10. Three variables are predictive characteristics. Smote_standardized_data is the result of traindata's basic processing, KNN filling missing values, outlier processing, standardization and balancing with SMOTE algorithm.