Managing credit risk in financial institutions requires the ability to
forecast aggregate losses on existing loans, predict the length of ti
me that loans will be on the books before prepayment or default, analy
ze the expected performance of particular segments in the existing por
tfolio, and project payment patterns of new loans. Described in this p
aper are tools created for these functions in a large California finan
cial institution. A forecasting model with Markovian structure and non
stationary transition probabilities is used to model the life of a mor
tgage. Logistic and regression models are used to estimate severity of
losses. These models are integrated into a system that allows analyst
s and managers to depict the expected performance of individual loans
and portfolio segments under different economic scenarios. With this i
nformation, analysts and managers can establish appropriate loss reser
ves, suggest pricing differentials to compensate for risk, and make st
rategic lending decisions.