An extensive evaluation of seven machine learning methods for rainfall prediction in weather derivatives

作者：

Highlights：

• An extensive evaluation of machine learning methods.

• Predictive performance not affected between Europe and the USA.

• Some linear relationships exists between error and climate.

• Machine learning methods outperform state-of-the-art.

摘要

•An extensive evaluation of machine learning methods.•Predictive performance not affected between Europe and the USA.•Some linear relationships exists between error and climate.•Machine learning methods outperform state-of-the-art.

论文关键词：Weather derivatives,Rainfall,Machine learning

论文评审过程：Received 4 February 2017, Revised 26 April 2017, Accepted 11 May 2017, Available online 12 May 2017, Version of Record 22 May 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.05.029