An extreme bias-penalized forecast combination approach to commodity price forecasting
文献类型:期刊论文
作者 | Zhang, Yifei1,2; Wang, Jue1,2; Yu, Lean3; Wang, Shouyang1,2 |
刊名 | INFORMATION SCIENCES |
出版日期 | 2022-11-01 |
卷号 | 615页码:774-793 |
ISSN号 | 0020-0255 |
关键词 | Forecast combination Elastic net Extreme bias Weight-sparsity Artificial bee colony algorithm |
DOI | 10.1016/j.ins.2022.09.056 |
英文摘要 | Forecast combination, a well-established technique for improving forecasting accuracy, investigates the integration of competing forecasts to produce a composite superior to individual forecasts. In this study, we propose a novel forecast combination method that would reduce overfitting risk and improve forecast's generalization ability. To capture the extreme bias of a forecast in combination process, we define a measurement PaR for forecast combination. A novel PaR-based loss function with an elastic net is proposed that can effectively trade off the sparsity of weights to mitigate the risk of underfitting or over -fitting. An improved artificial bee colony algorithm-based optimization method is intro-duced to achieve the optimal weights. The experimental results on gold, silver and crude oil price data demonstrate that the proposed forecast combination approach can outper-form not only individual models but also combination approaches like simple averaging and other competitive benchmarks. The MAPE achieved by the presented method could decrease by 10.98%, 5.03% and 10.28% in gold, silver and crude oil price forecasting respec-tively, compared to the best individual model.(c) 2022 Elsevier Inc. All rights reserved. |
资助项目 | National Center for Mathematics and Interdisciplinary Sciences (NCMIS) , Chinese Academy of Sciences (CAS) ; National Natural Science Foundation of China (NSFC)[71771208] ; National Natural Science Foundation of China (NSFC)[72271229] ; National Natural Science Foundation of China (NSFC)[71988101] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ELSEVIER SCIENCE INC |
WOS记录号 | WOS:000880802700002 |
源URL | [http://ir.amss.ac.cn/handle/2S8OKBNM/60680] |
专题 | 中国科学院数学与系统科学研究院 |
通讯作者 | Wang, Jue |
作者单位 | 1.Chinese Acad Sci, Acad Math & Syst Sci, CFS, MADIS, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 3.Sichuan Univ, Business Sch, Chengdu 610065, Peoples R China |
推荐引用方式 GB/T 7714 | Zhang, Yifei,Wang, Jue,Yu, Lean,et al. An extreme bias-penalized forecast combination approach to commodity price forecasting[J]. INFORMATION SCIENCES,2022,615:774-793. |
APA | Zhang, Yifei,Wang, Jue,Yu, Lean,&Wang, Shouyang.(2022).An extreme bias-penalized forecast combination approach to commodity price forecasting.INFORMATION SCIENCES,615,774-793. |
MLA | Zhang, Yifei,et al."An extreme bias-penalized forecast combination approach to commodity price forecasting".INFORMATION SCIENCES 615(2022):774-793. |
入库方式: OAI收割
来源:数学与系统科学研究院
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。