首页

首页 > 学术科研 > 正文

首页

学术科研
战略所人物
活动会议
合作交流
战略所动态
通知公告
视频

学术科研

Optimal starting point for time series forecasting

题目Optimal starting point for time series forecasting
作者Zhong, Yiming; Ren, Yinuo; Cao, Guangyao; Li, Feng; Qi, Haobo
作者单位Cent Univ Finance & Econ, Sch Stat & Math, Beijing 100081, Peoples R China Univ Chinese Acad Sci, Sch Adv Interdisciplinary Sci, Beijing 100049, Peoples R China Cent Univ Finance & Econ, Smart Campus Construct Ctr, Beijing 100081, Peoples R China Peking Univ, Guanghua Sch Management, Beijing 100871, Peoples R China Beijing Normal Univ, Sch Stat, Beijing 100875, Peoples R China
关键词：CONCEPT DRIFT
时间：2025年5月10日
出版者：EXPERT SYSTEMS WITH APPLICATIONS
摘要Recent advances on time series forecasting mainly focus on improving the forecasting models themselves. However, when the time series data suffer from potential structural breaks or concept drifts, the forecasting performance might be significantly reduced. In this paper, we introduce a novel approach called Optimal Starting Point Time Series Forecast (OSP-TSP) for optimal forecasting, which can be combined with existing time series forecasting models. By adjusting the sequence length via leveraging the XGBoost and LightGBM models, the proposed approach can determine the optimal starting point (OSP) of the time series and then enhance the prediction performances of the base forecasting models. To illustrate the effectiveness of the proposed approach, comprehensive empirical analysis have been conducted on the M4 dataset and other real world datasets. Empirical results indicate that predictions based on the OSP-TSP approach consistently outperform those using the complete time series dataset. Moreover, comparison results reveals that combining our approach with existing forecasting models can achieve better prediction accuracy, which also reflect the advantages of the proposed approach.
URLhttp://hdl.handle.net/20.500.11897/740453
ISSN0957-4174
DOI10.1016/j.eswa.2025.126798
收录情况SCI€
作者单位 Cent Univ Finance & Econ, Sch Stat & Math, Beijing 100081, Peoples R China Univ Chinese Acad Sci, Sch Adv Interdisciplinary Sci, Beijing 100049, Peoples R China Cent Univ Finance & Econ, Smart Campus Construct Ctr, Beijing 100081, Peoples R China Peking Univ, Guanghua Sch Management, Beijing 100871, Peoples R China Beijing Normal Univ, Sch Stat, Beijing 100875, Peoples R China 时间 2025年5月10日
出版者 EXPERT SYSTEMS WITH APPLICATIONS URL http://hdl.handle.net/20.500.11897/740453
ISSN 0957-4174 DOI 10.1016/j.eswa.2025.126798
收录情况 SCI€ 分类
TOP