Improving CAT bond pricing models via machine learning

Tobias Götze,Marc Gürtler,Eileen Witowski

doi:10.1057/s41260-020-00167-0

Tobias Götze, Marc Gürtler + Show 1 more

Open Access

https://doi.org/10.1057/s41260-020-00167-0

Copy DOI

Abstract

Enhanced machine learning methods provide an encouraging alternative to forecast asset prices by extending or generalizing the possible model specifications compared to conventional linear regression methods. Even if enhanced methods of machine learning in the literature often lead to better forecasting quality, this is not clear for small asset classes, because in small asset classes enhanced machine learning methods may potentially over-fit the in-sample data. Against this background, we compare the forecasting performance of linear regression models and enhanced machine learning methods in the market for catastrophe (CAT) bonds. We use linear regression with variable selection, penalization methods, random forests and neural networks to forecast CAT bond premia. Among the considered models, random forests exhibit the highest forecasting performance, followed by linear regression models and neural networks.

Highlights

Empirical models to forecast the future price of financial assets are predominantly based on linear regression models (Campbell and Thompson 2007; Rapach et al 2010; Thornton and Valente 2012)
2002–2006 2003–2007 2004–2008 2005–2009 2006–2010 2007–2011 2008–2012 2009–2013 2010–2014 2011–2015 2012–2016 Mean Median SD. This table reports the root mean squared error (RMSE) of the out-of-sample estimation for the full linear regression model, which is based on Braun (2016) and Gürtler et al (2016), the reduced model after the three-step selection, linear regression with variable selection, penalized regression, random forests (RF) and neural network (NN) models
2002–2006 2003–2007 2004–2008 2005–2009 2006–2010 2007-2011 2008–2012 2009–2013 2010–2014 2011–2015 Mean Median SD

Summary

Introduction

Empirical models to forecast the future price of financial assets are predominantly based on linear regression models (Campbell and Thompson 2007; Rapach et al 2010; Thornton and Valente 2012). We develop both linear regression- and enhanced machine learning-based forecasting models for risk premia in the market for CAT bonds.

Results

Conclusion