Decomposing USDA ending stocks forecast errors

The U.S. Department of Agriculture (USDA) publishes monthly Ending Stocks projections,providing an estimate of the end-of-marketing-year inventory of a particular commodity, which effectively summarizes its supply and demand outlook. By comparing USDA’s projections of balance sheet variables against...

Descripción completa

Detalles Bibliográficos
Autores principales: Goyal, Raghav, Adjemian, Michael K., Glauber, Joseph W., Meyer, Seth
Formato: Journal Article
Lenguaje:Inglés
Publicado: 2023
Materias:
Acceso en línea:https://hdl.handle.net/10568/140422
_version_ 1855514878192648192
author Goyal, Raghav
Adjemian, Michael K.
Glauber, Joseph W.
Meyer, Seth
author_browse Adjemian, Michael K.
Glauber, Joseph W.
Goyal, Raghav
Meyer, Seth
author_facet Goyal, Raghav
Adjemian, Michael K.
Glauber, Joseph W.
Meyer, Seth
author_sort Goyal, Raghav
collection Repository of Agricultural Research Outputs (CGSpace)
description The U.S. Department of Agriculture (USDA) publishes monthly Ending Stocks projections,providing an estimate of the end-of-marketing-year inventory of a particular commodity, which effectively summarizes its supply and demand outlook. By comparing USDA’s projections of balance sheet variables against their realized values from marketing years 1992/3 to 2019/20, we decompose ending stocks forecast errors into errors of the other supply and demand components. We apply a decision-tree-based ensemble Machine Learning (ML) algorithm, the Extreme Gradient Boost Tree (EGBT), that uses a gradient boosting framework and is robust to multicollinearity. Our results indicate that export and production misses are the key contributors to ending stocks projection errors. Because foreign imports of U.S. products are likely tied to foreign production beficits, we likewise investigate how U.S. export errors are linked to USDA’s foreign production and export forecast misses, country-by-country, and show that misses on production and export levels in China, Mexico, Brazil, and European Union cost USDA the most. Overall, our results make a strong case that better information about production expectations, both domestically and worldwide, will contribute to more efficient agricultural balance sheet forecasts.
format Journal Article
id CGSpace140422
institution CGIAR Consortium
language Inglés
publishDate 2023
publishDateRange 2023
publishDateSort 2023
record_format dspace
spelling CGSpace1404222024-11-13T12:23:07Z Decomposing USDA ending stocks forecast errors Goyal, Raghav Adjemian, Michael K. Glauber, Joseph W. Meyer, Seth production frameworks forecasting surveys machine learning slope stocks artificial intelligence agricultural prices agriculture economics economic activities agricultural economics commodity markets The U.S. Department of Agriculture (USDA) publishes monthly Ending Stocks projections,providing an estimate of the end-of-marketing-year inventory of a particular commodity, which effectively summarizes its supply and demand outlook. By comparing USDA’s projections of balance sheet variables against their realized values from marketing years 1992/3 to 2019/20, we decompose ending stocks forecast errors into errors of the other supply and demand components. We apply a decision-tree-based ensemble Machine Learning (ML) algorithm, the Extreme Gradient Boost Tree (EGBT), that uses a gradient boosting framework and is robust to multicollinearity. Our results indicate that export and production misses are the key contributors to ending stocks projection errors. Because foreign imports of U.S. products are likely tied to foreign production beficits, we likewise investigate how U.S. export errors are linked to USDA’s foreign production and export forecast misses, country-by-country, and show that misses on production and export levels in China, Mexico, Brazil, and European Union cost USDA the most. Overall, our results make a strong case that better information about production expectations, both domestically and worldwide, will contribute to more efficient agricultural balance sheet forecasts. 2023-05-01 2024-03-14T12:09:29Z 2024-03-14T12:09:29Z Journal Article https://hdl.handle.net/10568/140422 en Open Access Goyal, Raghav; Adjemian, Michael K.; Glauber, Joseph W.; and Meyer, Seth. 2023. Decomposing USDA ending stocks forecast errors. Journal of Agricultural and Resource Economics 48(2): 260-276. https://purl.umn.edu/320674
spellingShingle production
frameworks
forecasting
surveys
machine learning
slope
stocks
artificial intelligence
agricultural prices
agriculture
economics
economic activities
agricultural economics
commodity markets
Goyal, Raghav
Adjemian, Michael K.
Glauber, Joseph W.
Meyer, Seth
Decomposing USDA ending stocks forecast errors
title Decomposing USDA ending stocks forecast errors
title_full Decomposing USDA ending stocks forecast errors
title_fullStr Decomposing USDA ending stocks forecast errors
title_full_unstemmed Decomposing USDA ending stocks forecast errors
title_short Decomposing USDA ending stocks forecast errors
title_sort decomposing usda ending stocks forecast errors
topic production
frameworks
forecasting
surveys
machine learning
slope
stocks
artificial intelligence
agricultural prices
agriculture
economics
economic activities
agricultural economics
commodity markets
url https://hdl.handle.net/10568/140422
work_keys_str_mv AT goyalraghav decomposingusdaendingstocksforecasterrors
AT adjemianmichaelk decomposingusdaendingstocksforecasterrors
AT glauberjosephw decomposingusdaendingstocksforecasterrors
AT meyerseth decomposingusdaendingstocksforecasterrors