Identification of economic risks in international trade based on RF-Gini coefficients Research

Abstract

The rapid development of economic globalization objectively promotes the prosperity of international trade, which brings challenges and opportunities for China's economic construction. Based on China's macroeconomic data and foreign trade data, this paper uses the random forest (RF) regression algorithm for training and optimizes iterations for different step sizes by adjusting the number of decision trees to obtain the model with the best fit, and later investigates the strength of each factor's influence on international trade through the Gini coefficient. The results show that the exchange rate (0.128), the Engel coefficient of residential households (0.128), and the consumer price index (0.128) have a greater impact on the international trade economy. Thus, to maximize the stability of international trade risks, the state needs to control the inflation rate, focus on the efficient and coordinated development of the country's internal economy, and work to ensure that the nation has the basic consumption capacity, consumption needs, and create a favorable consumption environment.