<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>International trade is an important part of the world economy, and the rapid development of big data and complex network theory provides the possibility of an in-depth study of international trade networks. This study constructs the international trade flow gravity model and international trade flow index system on the basis of the clustered dynamic panel gravity model. It explores the influencing factors of national trade flow and the fitting effect of the international trade gravity model through factor analysis and regression analysis of variables in the system. The sample data’s KMO value is 0.834, according to the results, and there is a significant correlation between the variables. The degree of explanation of the public factors to the original variables is more than 0.5, and the variance contribution rate of trade structure, marketized structure, population and macroeconomics, international capital, and exchange rate reaches 71.832%, which makes the factor analysis more effective. The R² value of the trade gravity model reaches 0.837, with a remarkable effect. Among the sample countries, the highest trade flow potential is the United States (125,467.0), while the lowest is Portugal (512.4). The national GDP and population have a significant effect on international trade flows. The volume of each trading country should be used as a reference basis for conducting trade transactions when conducting international trade.</p>
</abstract>

International trade is an important part of the world economy, and the rapid development of big data and complex network theory provides the possibility of an in-depth study of international trade networks. This study constructs the international trade flow gravity model and international trade flow index system on the basis of the clustered dynamic panel gravity model. It explores the influencing factors of national trade flow and the fitting effect of the international trade gravity model through factor analysis and regression analysis of variables in the system. The sample data’s KMO value is 0.834, according to the results, and there is a significant correlation between the variables. The degree of explanation of the public factors to the original variables is more than 0.5, and the variance contribution rate of trade structure, marketized structure, population and macroeconomics, international capital, and exchange rate reaches 71.832%, which makes the factor analysis more effective. The R² value of the trade gravity model reaches 0.837, with a remarkable effect. Among the sample countries, the highest trade flow potential is the United States (125,467.0), while the lowest is Portugal (512.4). The national GDP and population have a significant effect on international trade flows. The volume of each trading country should be used as a reference basis for conducting trade transactions when conducting international trade.

Research on international trade flow analysis based on potential clustering network

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

International trade is an important part of the world economy, and the rapid development of big data and complex network theory provides the possibility of an...

Research on international trade flow analysis based on potential clustering network

Online veröffentlicht: 07. Juni 2024

Seitenbereich: -

Eingereicht: 14. Feb. 2024

Akzeptiert: 28. Apr. 2024

DOI: https://doi.org/10.2478/amns-2024-1387

Schlüsselwörter
Clustered dynamic panel, Factor analysis, Regression analysis, International trade

© 2024 Pan Yi, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Research on international trade flow analysis based on potential clustering network

Online veröffentlicht: 07. Juni 2024

Seitenbereich: -

Eingereicht: 14. Feb. 2024

Akzeptiert: 28. Apr. 2024

DOI: https://doi.org/10.2478/amns-2024-1387

SchlüsselwörterClustered dynamic panel, Factor analysis, Regression analysis, International trade

© 2024 Pan Yi, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Schlüsselwörter
Clustered dynamic panel, Factor analysis, Regression analysis, International trade