Bank supervisors in the United States conduct comprehensive on-site inspections of bank holding companies (BHCs) and assign them a supervisory rating meant to summarize their overall condition. We develop an empirical forecasting model of these ratings that combines supervisory and securities market data. We find that securities market variables, such as BHC stock returns and bond yield spreads, improve the model’s in-sample fit. We also find that debt market variables provide more information on supervisory ratings for BHCs closer to default, while equity market variables provide more information for those further from default. In out-of sample forecasting, we find that the accuracy of the model with both equity and debt variables is little different from the accuracy of a model based on supervisory information alone. However, the model with securities market data identifies additional ratings downgrades, which supervisors would probably value enough to warrant the use of this extended model for off-site monitoring purposes.