A Comparison between Wavelet Networks and Genetic Programming in the Context of Temperature Derivatives

The purpose of this study is to develop a model that accurately describes the dynamics of the daily average temperature 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, against the classic linear approaches widely used in the pricing of temperature derivatives in the financial weather market and against 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 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 significantly outperform the alternative linear models, with wavelet networks ranking first, and can be used for accurate weather derivative pricing in the weather market.