A deep factor model for crop yield forecasting and insurance ratemaking
Effective agricultural insurance and risk management programs rely on accurate crop yield forecasting. In this article, a novel deep factor model for crop yield forecasting and crop insurance ratemaking is proposed. This framework first utilizes a deep autoencoder to extract a latent factor, called...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/170183 |
| _version_ | 1811694467983343616 |
|---|---|
| author | Zhu, Wenjun |
| author2 | Nanyang Business School |
| author_facet | Nanyang Business School Zhu, Wenjun |
| author_sort | Zhu, Wenjun |
| collection | NTU |
| description | Effective agricultural insurance and risk management programs rely on accurate crop yield forecasting. In this article, a novel deep factor model for crop yield forecasting and crop insurance ratemaking is proposed. This framework first utilizes a deep autoencoder to extract a latent factor, called the 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. Empirical results show that the newly proposed deep factor model significantly improves the prediction accuracy, especially in the test set. Based on a retain–cede 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 Risk Management Agency ratemaking methodology. |
| first_indexed | 2024-10-01T07:08:03Z |
| format | Journal Article |
| id | ntu-10356/170183 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:08:03Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1701832023-08-31T01:18:57Z A deep factor model for crop yield forecasting and insurance ratemaking Zhu, Wenjun Nanyang Business School Business::Finance Crop Insurance Weather Derivatives Effective agricultural insurance and risk management programs rely on accurate crop yield forecasting. In this article, a novel deep factor model for crop yield forecasting and crop insurance ratemaking is proposed. This framework first utilizes a deep autoencoder to extract a latent factor, called the 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. Empirical results show that the newly proposed deep factor model significantly improves the prediction accuracy, especially in the test set. Based on a retain–cede 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 Risk Management Agency ratemaking methodology. Ministry of Education (MOE) Nanyang Technological University The author is grateful for the research funding support from the Nanyang Technological University Start-Up Grant (04INS000384C300), Singapore Ministry of Education Academic Research Fund Tier 1 (RG143/19), and the Society of Actuaries Education Institution Grant. 2023-08-31T01:18:57Z 2023-08-31T01:18:57Z 2023 Journal Article Zhu, W. (2023). A deep factor model for crop yield forecasting and insurance ratemaking. North American Actuarial Journal. https://dx.doi.org/10.1080/10920277.2023.2182792 1092-0277 https://hdl.handle.net/10356/170183 10.1080/10920277.2023.2182792 2-s2.0-85152364862 en 04INS000384C300 RG143/19 North American Actuarial Journal © 2023 Society of Actuaries. All rights reserved. |
| spellingShingle | Business::Finance Crop Insurance Weather Derivatives Zhu, Wenjun A deep factor model for crop yield forecasting and insurance ratemaking |
| title | A deep factor model for crop yield forecasting and insurance ratemaking |
| title_full | A deep factor model for crop yield forecasting and insurance ratemaking |
| title_fullStr | A deep factor model for crop yield forecasting and insurance ratemaking |
| title_full_unstemmed | A deep factor model for crop yield forecasting and insurance ratemaking |
| title_short | A deep factor model for crop yield forecasting and insurance ratemaking |
| title_sort | deep factor model for crop yield forecasting and insurance ratemaking |
| topic | Business::Finance Crop Insurance Weather Derivatives |
| url | https://hdl.handle.net/10356/170183 |
| work_keys_str_mv | AT zhuwenjun adeepfactormodelforcropyieldforecastingandinsuranceratemaking AT zhuwenjun deepfactormodelforcropyieldforecastingandinsuranceratemaking |