Improving CAT bond pricing models via machine learning

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.

Do crude oil futures still fuel portfolio performance?

“…Because our sample starts in 2003 and we require a large estimation window, we obtain 14 time series (7 stock-bond strategies and 7 stock-bond-oil strategies) of 24 monthly out-of-sample portfolio returns each. While, at first glance, this series length may appear small, it is widely accepted in research on investment funds performance and statistical investment support models (see Dunis et al, 2013;Eling, 2009;Götze et al, 2020) and, more importantly, will additionally be addressed by significance tests capable of handling such sample sizes. In line with Daskalaki and Skiadopoulos (2011) and Daskalaki et al (2017), we compare the performance of the traditional and the commodity-augmented portfolios by means of their out-of-sample Sharpe ratios (i.e., the sample mean of the excess returns divided by the sample standard deviation of the excess returns).…”