We develop a stock-flow-consistent agent-based model that comprises a realistic mechanism of money creation and parametrize it to fit actually observed data. The model is used to make out-of-sample projections of broad money and credit developments under the commencement/termination of foreign...

Model selection and forecasting in stress tests can be facilitated using machine learning techniques. These techniques have proved robust in other fields for dealing with the curse of dimensionality, a situation often encountered in applied stress testing. Lasso regressions, in particular, are...

Model selection and forecasting in stress tests can be facilitated using machine learning techniques. These techniques have proved robust in other fields for dealing with the curse of dimensionality, a situation often encountered in applied stress testing. Lasso regressions, in particular, are...

PD curve calibration refers to the transformation of a set of rating grade level probabilities of default (PDs) to another average PD level that is determined by a change of the underlying portfolio-wide PD. This paper presents a framework that allows to explore a variety of calibration...

We use a dynamic panel Tobit model with heteroskedasticity to generate point, set, and density forecasts for a large cross-section of short time series of censored observations. Our fully Bayesian approach allows us to flexibly estimate the cross-sectional distribution of heterogeneous...

We develop a model to predict consumer default based on deep learning. We show that the model consistently outperforms standard credit scoring models, even though it uses the same data. Our model provides favorable credit risk assessment to young borrowers relative to standard credit scoring...

We study how to perform tests on samples of pairs of observations and predictions in order to assess whether or not the predictions are prudent. Prudence requires that that the mean of the difference of the observation-prediction pairs can be shown to be significantly negative. For safe...

We replicate three bank failure models (Martin (1977), Cole and White (2012), and DeYoung and Torna (2013)) and introduce a new predictive model along with several evaluation methods to compare their out-of-sample predictive accuracy. We find that the models are highly accurate individually, and...

We investigate whether banks rely on the information content in equity analysts' annual earnings forecasts when assessing the risk of potential borrowers. While a long literature finds that analysts provide useful information to market participants, it is not clear that banks, which have access...

The recovery rate on defaulted corporate bonds has a time-varying distribution. We propose machine learning approaches for intertemporal analysis of U.S. corporate bonds' recovery rates with a large number of predictors. The most informative macroeconomic variables are selected from a broad...