The impact of the Russia–Ukraine conflict on supply chain disruptions in Thailand's agricultural sector: an analysis of TVP-VAR network connectivity and price volatility prediction

Paritta Apithanaphuwadol, Konstantinos Nikolopoulos and Vasileios Bougioukos

Chapter 2 in Forecasting, Planning and Strategy in a Turbulent Era, 2025, pp 58-95 from Edward Elgar Publishing

Abstract: This chapter explores the implications of the Russia–Ukraine conflict on Thailand's agricultural sectors. The Time-Varying Parameter Vector Autoregressive (TVP-VAR) approach is employed to investigate the volatility connectedness network between the global commodities and Thailand's agricultural sector before and during the conflict, utilizing daily data from 1 January 2019, to 31 July 2023. The findings indicate that the overall interconnectedness of volatility increases during the Russia–Ukraine conflict compared to the period before the conflict. This suggests that the conflict strengthened the connectedness between the global commodities and the agricultural products in Thailand. The global commodities, S&P GSCI Wheat, S&P GSCI Soybean, S&P GSCI Crude Oil, and S&P GSCI Natural Gas, are primary net transmitters of volatility spillovers during the conflict period. Moreover, due to the conflict, Soybean Meal, Shrimp, Chicken, and Pork became net transmitters, while Maize, Cassava, Garlic, and Fish assumed the role of net receivers of volatility. These findings provide policymakers with insights into how the conflict impacts different products. This research incorporates forecast models to predict price volatility for twelve commodities. It utilizes GARCH (1,1) and machine learning models, including LSTM and XGBoost, with grid search applied for hyperparameter optimization on the S&P GSCI Wheat dataset. The evaluation is based on RMSE, MAE, and 〖R 〗^2 metrics. The results show the superior performance of the XGBoost model in terms of RMSE and MAE, while the LSTM model outperforms based on R^2. Leveraging the potential of these models provides policymakers with an effective means to predict fluctuations in commodity prices. Overall, the combination of the TVP-VAR analysis and advanced forecast models equips the Thai government with a comprehensive set of resources to navigate the challenges posed by the conflict. This enables them to implement timely and effective measures, safeguarding the stability of agricultural sectors, supporting farmers and producers, and ensuring the availability of essential products in the country.

Keywords: Thailand; Russia–Ukraine conflict; Global commodities; Agriculture; Consumption patterns (search for similar items in EconPapers)
Date: 2025
ISBN: 9781035317233
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.elgaronline.com/doi/10.4337/9781035317240.00007 (application/pdf)
Our link check indicates that this URL is bad, the error code is: 403 Forbidden

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:elg:eechap:22585_3

Ordering information: This item can be ordered from
http://www.e-elgar.com

Access Statistics for this chapter

More chapters in Chapters from Edward Elgar Publishing
Bibliographic data for series maintained by Darrel McCalla ().