摘要
成品油企业实现准确加油站销量预测可降低企业库存成本和提升运营效率,这是进行智能主动配送的基础。现有加油站销量预测多为人工凭经验判断或利用平均值进行计算,预测准确度较低。本文提出一种基于决策树集成模型的加油站销量预测方法,利用积累的历史销售数据和相关特征数据进行计算,对加油站的销量进行预测,结果显示该模型给出的预测结果精度较高,能够满足企业的实际需求。
The realization of accurate gas station sales forecast by refined oil companies can reduce the inventory cost of enterprises and improve operational efficiency,which is the basis for intelligent and active distribution.Most of the existing gas station sales forecasts are calculated manually by experience or by using the average value,and the prediction accuracy is low.This paper proposes a gas station sales forecasting method based on the decision tree integration model,which uses the accumulated historical sales data and related feature data to calculate and predict the sales volume of the gas station.The results show that the prediction results given by the model are highly accurate and can meet the actual needs of enterprises.
作者
张晨
邱彤
ZHANG Chen;QIU Tong(Department of Chemical Engineering,Tsinghua University,Beijing 100084,China)
出处
《计算机与应用化学》
CAS
北大核心
2019年第6期615-619,共5页
Computers and Applied Chemistry
基金
国家自然科学基金(U1462206)。
关键词
销量预测
成品油
决策树
集成学习
sales forecast
refined oil
decision tree
integrated learning
