Research Article
Clustering-XGB Based Dynamic Time Series Prediction
@INPROCEEDINGS{10.1007/978-3-030-94182-6_25, author={Haoxuan Sun and Kun Zhang and Tingting Wang and Wanfeng Ma and Qinjun Zhao}, title={Clustering-XGB Based Dynamic Time Series Prediction}, proceedings={IoT and Big Data Technologies for Health Care. Second EAI International Conference, IoTCare 2021, Virtual Event, October 18-19, 2021, Proceedings, Part II}, proceedings_a={IOTCARE PART 2}, year={2022}, month={6}, keywords={Time series KMEANS clustering XGBoost}, doi={10.1007/978-3-030-94182-6_25} }- Haoxuan Sun
Kun Zhang
Tingting Wang
Wanfeng Ma
Qinjun Zhao
Year: 2022
Clustering-XGB Based Dynamic Time Series Prediction
IOTCARE PART 2
Springer
DOI: 10.1007/978-3-030-94182-6_25
Abstract
This work analyzes time series and find the rules and statistical characteristics from the numerous data. According to the purpose of the time series analysis, we find the rules and conduct the future time forecast. This paper is mainly based on the similarity of time series. Based on clustering results, XGB is used to reflect the relationship between similarity and clusters’ weights and to predict the value. Overall, it is a time series prediction model based on clustering and XGB regulated weights. The process of model prediction is realized by using instances in dataset, and the relationship between similarity and weights is obtained by using XGB.
Copyright © 2021–2025 ICST
