Quant Foundry execs Chris Cormack and David Kelly elaborate on a methodology for low probability default modeling using a neural network approach in a recent issue of Intelligent Risk, a publication from the Professional Risk Managers’ International Association.
The drivers underlying development of the methodology described in the article are challenges posed by regulators, and the desire of asset and treasury managers to improve their portfolio investment decisions for low profitability defaults (LPD) such as sovereigns, through improved forecasting methods.
LPD by definition happens infrequently and the available data is restricted, as there are no more than 200 sovereign issuers. Traditional statistical techniques that link disparate probability distributions are hampered by fragmented market data, with quality concentrated in developed country issuers.
Countries fail on their external obligations for many reasons, but there is a pattern of behavior that an analyst would look for in the anticipation that history does repeat itself. Examples include material expansion of external debt, ambitious infrastructure programs, autocratic or corrupt government, and low GDP per head of population. Market data such as yield curves provide a consensus of relative risk-reward from investors based on capital flows, but such data does not capture the whole and tends to understate the credit risk of sovereigns.
The expertise incorporated by the methodology designers combines industry credit risk knowledge, traditional analytical methods and deep understanding of neural network tools, to leverage off a wider selection of empirical data. The approach taken is to break down the thought process of a credit analyst who uses both market and non-market data indicators and replicate it using a model that provides a powerful, unbiased and potentially superior default predictor.