A Deep Factor Model for Crop Yield Forecasting and Insurance Ratemaking

Effective agricultural insurance and risk management program rely on accurate crop yield forecasting. In this paper, we propose a novel deep factor model for crop yield forecasting and crop insurance ratemaking. This framework first utilizes a deep autoencoder to extract a latent factor, called production index, that integrates salient spatial temporal patterns in the original yield data. Then, a concatenated deep learning model is constructed to enhance the modeling of the production index and the reconstruction of crop yields. Convolutional neural networks are employed to capture the high-dimensional and highly nonlinear structure within the crop yield data, as well as its interactions with weather and economic variables. The proposed deep factor framework is applied to the county-level data in the state of Iowa, U.S. Empirical results show that the newly proposed deep factor model significantly improve the prediction accuracy, espeically in the test set. Based on an out-of-sample crop insurance rating game between a private insurer and the government, we show that the proposed deep factor model provides economically and statistically significant improvement over the current RMA ratemaking methodology