A sound statistical model for recovery rates is required for various applications in quantitative risk management. We compare different models for predicting the recovery rate on borrower level including linear and quantile regressions, decision trees, neural networks and mixture regression models. We fit and apply these models on the worldwide largest loss and recovery dataset for commercial loans provided by Global Credit Data, where we focus on small- and medium-sized entities in the US. Additionally, we include macroeconomic information via a predictive Crisis Indicator. The horserace is won by the mixture regression model with regressed weight probabilities.     «

A sound statistical model for recovery rates is required for various applications in quantitative risk management. We compare different models for predicting the recovery rate on borrower level including linear and quantile regressions, decision trees, neural networks and mixture regression models. We fit and apply these models on the worldwide largest loss and recovery dataset for commercial loans provided by Global Credit Data, where we focus on small- and medium-sized entities in the US. Addi...     »