%0 Journal Article
%T 基于XGBoost模型产品订单量的预测<br>Prediction of Product Order Volume Based on XGBoost Model
%A 苏郅宏
%A 孙宇婷
%A 杨永铖
%A 黄航英
%A 金秀玲
%J Modeling and Simulation
%P 5177-5186
%@ 2324-870X
%D 2023
%I Hans Publishing
%R 10.12677/MOS.2023.126471
%X 把握供应链需求，提高资源配置和利用效率对企业树立竞争优势具有重大的实际意义。通过特征分析提取了特征变量后，建立XGBoost模型，利用GridSearchCV技术对模型进行调参优化，最终得到模型的拟合优度为0.956，均方根误差RMSE为36.522。同时我们还建立了随机森林模型进行对比，结果表明XGBoost模型效果更理想，因此最终根据所构建的XGBoost模型实现对企业未来三月产品订单量的预测，为企业合理安排生产计划提供了一定的理论依据。<br />
Grasping supply chain demand, improving resource allocation and utilization efficiency is of great practical significance for enterprises to establish competitive advantage. After extracting charac-teristic variables through feature analysis, XGBoost model is established, and the model is adjusted and optimized using GridSearchCV technology. Finally, the goodness of fit of the model is 0.956, and the Root-mean-square deviation RMSE is 36.522. At the same time, we also established a Random forest model for comparison. The results indicate that the XGBoost model has a more ideal effect. Therefore, based on the constructed XGBoost model, the prediction of the company’s product order volume in the next three months is ultimately achieved, providing a certain theoretical basis for the company to reasonably arrange production plans.
%K 产品订单量，XGBoost模型，随机森林，预测<br>Product Order Volume
%K XGBoost Model
%K Random Forest
%K Prediction
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=75007