A comparison of wavelet networks and genetic programming in the context of temperature derivatives

https://doi.org/10.1016/j.ijforecast.2016.07.002Get rights and content
Under a Creative Commons license
open access

Abstract

The purpose of this study is to develop a model that describes the dynamics of the daily average temperature accurately in the context of weather derivatives pricing. More precisely, we compare two state-of-the-art machine learning algorithms, namely wavelet networks and genetic programming, with the classic linear approaches that are used widely in the pricing of temperature derivatives in the financial weather market, as well as with various machine learning benchmark models such as neural networks, radial basis functions and support vector regression. The accuracy of the valuation process depends on the accuracy of the temperature forecasts. Our proposed models are evaluated and compared, both in-sample and out-of-sample, in various locations where weather derivatives are traded. Furthermore, we expand our analysis by examining the stability of the forecasting models relative to the forecasting horizon. Our findings suggest that the proposed nonlinear methods outperform the alternative linear models significantly, with wavelet networks ranking first, and that they can be used for accurate weather derivative pricing in the weather market.

Keywords

Weather derivatives
Wavelet networks
Temperature derivatives
Genetic programming
Modelling
Forecasting

Cited by (0)

Antonios K. Alexandridis is a Lecturer in Finance at the School of Mathematics, Statistics and Actuarial Science, University of Kent, UK. His research interests are close related to Artificial Intelligence and Financial Engineering. So far, he has published several research papers in leading, international and well recognized journals. He has also authored 2 books in the area of weather derivatives and wavelet networks (Springer: Weather Derivatives: Modeling and Pricing Weather-Related Risk, Wiley: Wavelet Neural Networks: Methodology and Applications in Financial Engineering, Classification and Chaos).

Michael Kampouridis is a lecturer at the School of Computing at the University of Kent, UK. His main research interests lie on the intersection of Computational Intelligence and Computational Finance. Areas of particular interest include algorithmic trading, financial forecasting, and intelligent decision support systems.

Sam Cramer is a Ph.D. student at the School of Computing at the University of Kent, UK. His main research interests lie on the intersection of Computational Intelligence and Computational Finance. Areas of particular interest include weather derivatives, financial forecasting, and intelligent decision support systems.