datanalysis▌

Credit risk data cleaning and variable screening pipeline for pre-loan modeling. \n \n Executes 11 independent steps covering data loading, abnormal period filtering, missing rate analysis, low-IV and high-PSI variable removal, null importance denoising, and correlation-based feature elimination \n Supports organization-level analysis with separate modeling and out-of-sample (OOS) sample handling, plus multi-process acceleration for IV and PSI calculations \n Generates comprehensive Excel report