The United States’ Clothing Imports from Asian Countries along the Belt and Road: An Extended Gravity Trade Model with Application of Artificial Neural Network

Abstract

In 2013, China announced the Belt and Road Initiative (BRI), which aims to promote the connectivity of Asia, Europe, and Africa and deepen mutually beneficial economic cooperation among member countries. Past studies have reported a positive impact of the BRI on trade between China and its partner countries along the Belt and Road (B&R). However, less is known about its effect on the sectoral trade between the B&R countries and countries that show little support of the BRI. To address that gap, this study examines the changing patterns of clothing imports by the United States (US) from China and 14 B&R countries in Asia. An extended gravity model with a policy variable BRI is built to explain bilateral clothing trade flow. A panel regression model and artificial neural network (ANN) are developed based on the data collected from 1998 to 2018 and applied to predict the trade pattern of 2019. The results show a positive effect of the BRI on the clothing exports of some Asian developing countries along the B&R to the US and demonstrate the superior predictive power of the ANN. More research is needed to examine the balance between economic growth and the social and environmental sustainability of developing countries and to apply more advanced machine learning algorithms to examine global trade flow under the BRI.

Quantitative Dynamics Effects of Belt and Road Economies Trade Using Structural Gravity and Neural Networks

“…Our preliminary results show the main findings below: The neural network (NN) has a high degree of accuracy in prediction compared with the SGM in terms of root mean square error (RMSE), which is in line with Wohl and Kennedy (2018) and Ho et al (2020). China’s trade growth effects slightly increase over time under the BRI pointing to the importance of using panel data for trade policy evaluation.…”

“…The BRI was officially launched in 2013; however, projects started years earlier are often considered (Hillman, 2018; Ho et al, 2020; Huang & Li, 2020). The analysis covers a panel data set of 163 countries over the years 1990 to 2017.…”

“…The BRI was officially launched in 2013; however, projects started years earlier are often considered (Hillman, 2018;Ho et al, 2020;Huang & Li, 2020 Agbodji (2008) and Carrère (2006) using four variables proxying the infrastructure from international road federation (IRF) world road statistics (WRS), 2018 and the world development indicators (2018). It is built as average of the density of road network, the rail network, paved road network, and the number of telephone main lines per person.…”

“…First, it explores a significant and underresearched field of bilateral trading within the schema of the BRI. Although some studies have dwelt on the trading activities in the ambit of the BRI over the years, the authors of these studies chiefly analyzed trade flows between China and its trading partners at the country level (Di Stefano et al, 2021; Ho et al, 2020). In other words, they failed to consider the intriguing trading activities between the BRI and non-BRI countries at the sectoral level to broaden the horizon on the subject matter.…”

“…Third, this study applies a novel approach in a form of machine learning algorithm and data mining concept (i.e., artificial neural network [ANN]) to analyze China’s BRI effects on trade flows and demonstrates how ANN complements the conventional econometric approach. The use of ANN in this study is relevant and valuable not only because of its higher predictive power but also because of its ability to estimate complex trade relationships (Ho et al, 2020; Wohl & Kennedy, 2018). Stated differently, machine learning techniques are poised with the propensity to address the limitations of traditional econometrics.…”