This study analyzes different parametric and non-parametric modeling methods for estimating the Loss Given Default (LGD) of bank loans for shipping companies. The shipping industry is subject to several different risks which create the need to accurately measure the possible losses in order to estimate the LGDs for the banking industry. We use a unique database of defaulted loans in European banks involved in shipping finance. The aim of this study is twofold: to compare the performance of alternative LGD modeling methodologies in shipping finance and to provide some insights into what drives LGD in the shipping industry. We find that non-parametric methods, especially random forest, lead to a remarkable increase in the prediction accuracy and outperform the traditional statistical models in terms of both in-sample and out-of-sample results. To investigate the risk drivers in the shipping business, we use a variable importance measure built on the idea of the permutation importance. We find the energy index to be of paramount importance and the most important risk factor to estimate shipping finance LGD. We find that crude oil prices play a big role and may affect the financial health of shipping firms and then the LGDs of shipping loans.
Parole Chiave: 
Loss Given Default, Shipping Finance, Forecasting, Machine Learning, Global Credit Data.
Tipo di pubblicazione: 
Rapporto Tecnico
Codice Pubblicazione: 
Allegato Pubblicazione: