An Application of a Three‐Stage XGBoost‐Based Model to Sales Forecasting of a Cross‐Border E‐Commerce Enterprise

Abstract

Sales forecasting is even more vital for supply chain management in e-commerce with a huge amount of transaction data generated every minute. In order to enhance the logistics service experience of customers and optimize inventory management, e-commerce enterprises focus more on improving the accuracy of sales prediction with machine learning algorithms. In this study, a C-A-XGBoost forecasting model is proposed taking sales features of commodities and tendency of data series into account, based on the XGBoost model. A C-XGBoost model is first established to forecast for each cluster of the resulting clusters based on two-step clustering algorithm, incorporating sales features into the C-XGBoost model as influencing factors of forecasting. Secondly, an A-XGBoost model is used to forecast the tendency with the ARIMA model for the linear part and the XGBoost model for the nonlinear part. The final results are summed by assigning weights to forecasting results of the C-XGBoost and A-XGBoost models. By comparison with the ARIMA, XGBoost, C-XGBoost, and A-XGBoost models using data from Jollychic cross-border e-commerce platform, the C-A-XGBoost is proved to outperform than other four models.

RETRACTED ARTICLE: Optimization model design of cross-border e-commerce transportation path under the background of prevention and control of COVID-19 pneumonia

“…Therefore, it is of great practical significance to study the export route optimization of manufactured goods under cross-border electronic commerce. Starting from cross-border electronic commerce, this paper combs the development status of cross-border electronic commerce, analyzes its relationship with manufactured goods export, and introduces the main problems faced by China's manufactured goods export (Ji et al 2019 ). Taking Viva office chair export as an example, this paper discusses the specific methods of optimizing the export route of China's manufactured goods through cross-border electronic commerce, and analyzes how to realize the integration of cross-border electronic commerce's supply chain through the integration of cross-border electronic commerce's supply chain, the comprehensive foreign trade service platform and the optimization and upgrading of enterprises themselves, so as to promote the optimization of China's manufactured goods export route and the development of China's manufacturing industry.…”

A Genetic Programming-Driven Data Fitting Method

“…In [7], XGBoost, a typical boosting algorithm, is used to avoid overfitting problems and establish an efficient energy load prediction model in residential buildings. Based on XGBoost, a C-A-XGBoost sales prediction model was proposed for focusing on the characteristics of commodity sales and the trend fitting of data series [8]. The experimental results suggest that the prediction is more accurate.…”

Intelligent IoT‐Based Cross‐Border e‐Commerce Supply Chain Performance Optimization

“…When things happen, it is necessary to hold a certain cost inventory [10]. Also, during the procurement and production period, in order not to interrupt the production process and maintain the continuity of production, cross-border ecommerce must have a certain amount of raw material 2 Wireless Communications and Mobile Computing inventory [11]. Due to many reasons, the amount of crossborder e-commerce inventory is often uncertain.…”