Research on Export Flow and Potential of Agricultural Products in China Based on Machine Learning Algorithm
DOI: https://doi.org/10.62517/jse.202411303
Author(s)
Zhenjun Cai*
Affiliation(s)
School of Business, Hunan International Economics University, Changsha, China
*Corresponding Author.
Abstract
The MLR (multiple linear regression) method in machine learning algorithm is a comprehensive method to study the correlation of variables, and it is also an important measure to study the relationship between variables by using linear fitting method. By combining qualitative analysis with quantitative analysis, this paper will use MLR model to make an empirical analysis of the determinants of agricultural trade flow, and use the estimated parameters to calculate the agricultural trade potential of China. The results show that the economic scale and distance have an important influence on the export flow of agricultural products in China, indicating that the economic scale is an important factor affecting the export flow of agricultural products. Regional trade arrangements have dual effects of trade transfer and trade creation, and free trade arrangements have created favorable conditions for trade expansion between countries with different demand and income levels. China's exports to Russia, Thailand, Singapore, the Philippines, Malaysia and Indonesia are in a state of deficiency, and there is still potential for developing agricultural products exports to these countries.
Keywords
Machine Learning; Multiple Linear Regression; Agricultural Products; Trade Potential
References
[1] Khan, Z. A., Koondhar, M. A., Aziz, N., Ali, U., & Tianjun, L. (2020). Revisiting the effects of relevant factors on Pakistan's agricultural products export. Agricultural Economics (AGRICECON), 66(12), 527-541.
[2] Peng, C., Zeng, Y., Huang, B., & Yabe, M. (2010). The contracts between leading agribusiness enterprises and rural households: its effects on firm-level export of agricultural products. Journal of the Faculty of Agriculture, Kyushu University, 2010(2), 55.
[3] Brindha, K. (2017). International virtual water flows from agricultural and livestock products of india. Journal of Cleaner Production, 161(10), 922-930.
[4] Bank, T. W. (2011). Supply chains in export agriculture, competition, and poverty in sub-saharan africa. European Review of Agricultural Economics, 2013(4), 123-185.
[5] Helena, Resano-Ezcaray, Ana, Isabel, Sanjuán-López, & Luis, et al. (2010). Combining stated and revealed preferences on typical food products: the case of dry-cured ham in spain. Journal of Agricultural Economics, 61(3), 480-498.
[6] Bedoic, R., Cosic, B., & Duic, N. (2019). Technical potential and geographic distribution of agricultural residues, co-products and by- products in the European Union. Science of The Total Environment, 686(10), 568-579.
[7] Ltd, C. P. (2012). Agricultural science and technology-meeting the challenge. Molecular Medicine Reports, 5(3), 651-654(4).
[8] Mcelwee, P. D. (2010). Resource use among rural agricultural households near protected areas in Vietnam: the social costs of conservation and implications for enforcement. Environmental Management, 45(1), 113-131.
[9] Qian, Y., Tian, X., Geng, Y., Zhong, S., Cui, X., & Zhang, X., et al. (2019). Driving factors of agricultural virtual water trade between china and the belt and road countries. Environmental Science and Technology, 53(10), 5877-5886.
[10] Huseyn, R., Latifova, E. N., Ismayilli, R. S., & Abbasov, V. H. (2021). Assessing the impact of the coronavirus pandemic on agricultural export. Journal of Agricultural Economics, 5(3), 19-30.
[11] Galani, Y. J. H., Houbraken, M., Wumbei, A., Djeugap, J. F., Fotio, D., & Gong, Y. Y., et al. (2020). Monitoring and dietary risk assessment of 81 pesticide residues in 11 local agricultural products from the 3 largest cities of Cameroon. Food Control, 2020(118), 118.
[12] Lee, H., & Sumner, D. A. (2011). South Korea-U.S. free trade agreement will lower export barriers for California products. California Agriculture, 65(2), 66-72
