Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Industrial Technological Economics》 2018-07
Add to Favorite Get Latest Update

Research on the Original Oil Price Prediction Based on Lasso-Xgboost Combination Method

Shi Guoliang;Jing Zhigang;Fan Liwei;School of Business,Hohai University;  
In view of the frequent fluctuation of international crude oil price and the importance of national economy,the study of oil price forecast and the influence factors of oil price has been a hot research topic at home and abroad. In order to improve the accuracy of forecast,in this article,on the basis of summing up the price influence factors,using Lasso method to selected 11 main influence factors such as U. S. oil production cost,WTI crude oil futures prices,China's crude oil production. Then Xgboost method is used to forecast oil prices. The results of numerical tests show that compared with other prediction methods,the LassoXgboost combination method constructed in this paper predicts higher precision and more generalization ability. Finally,we forecast the price of WTI crude oil price from 2018 to 2019 using trained model.
【Fund】: 国家自然科学基金资助项目“国际油价波动的独立源影响因素及其集成智能预测研究”(项目编号:71203055)
【CateGory Index】: F416.22;F764.1
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved