Since 1990, the banking sector has experienced enormous legislative, technological, and financial changes, yet research into the causes of bank distress has slowed. One consequence is that traditional supervisory surveillance models may not capture important risks inherent in the current banking environment. After reviewing the history of these models, the authors provide empirical evidence that the characteristics of failing banks have changed in the past ten years and argue that the time is right for new research that employs new empirical techniques. In particular, dynamic models that use forward-looking variables and address various types of bank risk individually are promising lines of inquiry. Supervisory agencies have begun to move in these directions, and the authors describe several examples of this new generation of early-warning models that are not yet widely known among academic banking economists.