Understanding Drivers Of Credit Risk
January 23, 2017 //
Differences and Similarities of the Credit Risk Assessment of a Non-Financial Corporation, via a Probability of Default and a Scoring Model
Since the introduction of Altman’s Z-score for U.S. corporations in 1968, there has been a proliferation of statistical models that combine financial ratios, socio, and macroeconomic factors with advanced mathematical techniques to estimate the credit-worthiness of publicly listed or privately held companies in a simplified, quick, automated, and scalable way.
Fundamentals-based credit risk models usually come in two flavours, depending on the asset class they aim to cover: Probability of Default (PD) models are trained and calibrated on default flags that are abundant for small and medium enterprises; scoring models exploit the ranking power of an established credit rating agency to estimate the credit score of low-default asset classes, such as high-revenue corporations or insurance companies.
At S&P Global Market Intelligence, we offer both types of statistical models: PD Model Fundamentals and CreditModelTM. PD Model Fundamentals is a Probability of Default model that covers publicly listed and privately owned corporations and banks, with no revenue and asset size limitation. CreditModel is a scoring model trained on the S&P Global Ratings, covering publicly listed and privately owned corporations, banks and insurance companies, with more than $25M in total revenue and $100M in total assets, respectively.
CreditModel and PD Model Fundamentals overlap in their coverage of medium and large corporations with more than $25M in revenue (banks over $100M in assets), and in certain instances can (and will) provide divergent credit risk assessments on the same company, with a difference at times of several credit score notches.
This should be no surprise, given that we are comparing the assessment from two different families of models (PD models vs scoring models) that were trained on different datasets (default flags vs S&P Global Ratings level), and are characterized by a different analytical “DNA” (the risk assessment is medium-term risk for PD models, with a stability of circa one year time horizon, and long-term for scoring models trained on ratings, with a stability of three to five years for investment grade scores, and two to three years for non-investment grade scores).
In the next sections, we will perform an in-depth analysis on the weak credit scores output by CreditModel and PD Model Fundamentals for non-financial corporations in North-America:
- For all models, the main drivers of a weak credit score refer to the size, the profitability, and the leverage/flexibility risk dimensions, but the actual ratios included in each model depend on the availability/coverage and their predictive power.
- Outputs from different models are aligned within one notch in the majority of cases, when the financial statement contains “weaknesses across the board”; marked divergences can be seen in limited instances, whenever a company financial statement presents a mixed profile, with some “strong” and some “weak” items.
 Altman, Edward I. (September 1968). “Financial Ratios, Discriminant Analysis and the Prediction of Corporate Bankruptcy”. Journal of Finance: 189-209.
 S&P Global Ratings does not contribute to or participate in the creation of credit scores generated by S&P Global Market Intelligence. Lowercase nomenclature is used to differentiate S&P Global Market Intelligence PD credit model scores from the credit ratings issued by S&P Global Ratings.