Skip to content

Latest commit

 

History

History
43 lines (25 loc) · 1.08 KB

README.md

File metadata and controls

43 lines (25 loc) · 1.08 KB
Raw

Credit-Risk-Models-PD-LGD-EAD-Expected-Loss

We calculate PD,LGD,EAD and Expected loss using logistic and beta regressions.

Notebook 1: Training dataset preparation (Feature engineering - Continuous and Discrete dataset)
Notebook 2: Test dataset preparation
Notebook 3: Calculate Probability of Default (POD) and Credit score card preparation
Notebook 4: Monitor the POD model
Notebook 5: Calculate LGD (Loss given dataset) and EAD (Exposure at Default)for individual customers
Notebook 6: Compute Expected Loss for individual customers

Dataset (Source:Lending Club)

  • loan_data_2007_2014 (Train dataset)
  • loan_data_2015 (Validation dataset)
  • loan_data_2007_2014_preprocessed (Preprocessed dataset)

Techniques covered in the model building:

  • Weight of evidence

  • Information value

  • Fine classing

  • Coarse classing

  • Linear regression

  • Logistic regression

  • Area Under the Curve

  • Receiver Operating Characteristic Curve

  • Gini Coefficient

  • Kolmogorov-Smirnov

  • Assessing Population Stability

  • Maintaining a model