Application of Gradient Boosting Regression Model in Intelligent Distribution of E-Commerce Platforms

Abstract

With the nation's e-commerce expanding quickly in recent years, the quantity of e-commerce purchases has continued to increase, and people's methods of consuming have also transformed. Digital shopping has lately been more practical and effective due to advancements in Internet innovation, particularly wireless connections, and 5G mobile connectivity technologies. Digital shopping has brought about the peak of globalization and has grown to be an essential sector of economic globalization. On the other hand, since e-commerce has grown rapidly, several issues have occurred. One of those is logistics distribution, it is an important component in the chain that affects customer fulfillment and has a big influence on e-commerce growth. Distribution in e-commerce pertains to the procedure of sending goods or commodities to the final customer after an online transaction. With e-commerce, efficient distribution is essential to ensure that goods are delivered to consumers promptly and effectively. This fosters user retention and encourages repeat purchases. It is necessary to provide an efficient model for the efficient e-commerce distribution. For an effective intelligent e-commerce distribution platform, we proposed the gradient boosting regression model (GBRM). The efficiency of the suggested system was assessed and contrasted with methods that were previously utilized. The results show that the suggested GBRM model significantly enhanced the distribution of e-commerce which generates a computation time of 60 and distribution speed of 90.