Discriminant Credit Models

Overview


Discriminant models were an early form of statistical classifiers. As such, they also formed the basis of the early credit models, the most famous being the Altman Z-score.

Altman Z-Score


The Altman Z-Score model is defined by the following equation.
{% Z = 0.012 x_1 + 0.014X_2 + 0.033 X_3 +0.006 X_4 + 0.999 X_5 %}
  • {% X_1 %} = working capital/total assets
  • {% X_2 %} = retained earnings/total assets
  • {% X_3 %} = earning before interest and taxes (EBIT)/total assets
  • {% X_4 %} = market value of equity/book value of total liabilities
  • {% X_5 %} = sales/total assets

A company with a Z-score below 1.81 is classified as bad in the initial study.