Research on a Time Series Forecasting Model Based on Multiple Regression and Polynomial Fitting
DOI:
https://doi.org/10.62051/pb4xdx35Keywords:
time series forecasting; formatting; multivariate regression analysis; polynomial approximation.Abstract
To address the inherent limitations of traditional time series forecasting models in handling complex real-world scenarios characterized by nonlinear dynamics and multivariate interactions, this paper proposes a novel hybrid prediction framework that synergistically integrates multivariate regression analysis with adaptive polynomial fitting mechanisms. First, outliers and missing values are processed through data cleaning technology. A feature system of many parameters such as event focus, new event participation rate, and host advantage growth coefficient is constructed. A prediction model based on polynomial regression is designed. And the parameter combination is optimized through cross-validation. The experimental results show that the mean square error of the model on the standard data set is lower than that of the traditional method, and the mean absolute error is reduced. The research results verify the effectiveness of the multi-model fusion strategy in nonlinear time series prediction and provide a new method for processing time series data.
Downloads
References
[1] KURISU D, FUKAMI R, KOIKE Y. Adaptive deep learning for nonlinear time series models[J]. Bernoulli, 2025, 31(1): 240-270. DOI: https://doi.org/10.3150/24-BEJ1726
[2] Dunwang Qin, Zhen Peng, Lifeng Wu. Deep attention fuzzy cognitive maps for interpretable multivariate time series prediction[J]. Knowledge-Based Systems, 2023, 275: 110700. DOI: https://doi.org/10.1016/j.knosys.2023.110700
[3] Bonas M, Datta A, Wikle C K, et al. Assessing predictability of environmental time series with statistical and machine learning models[J]. Environmetrics, 2025, 36(1): e2864. DOI: https://doi.org/10.1002/env.2864
[4] Z. Han, J. Zhao, H. Leung, K. F. Ma and W. Wang, "A Review of Deep Learning Models for Time Series Prediction," in IEEE Sensors Journal, vol. 21, no. 6, pp. 7833-7848, 15 March15, 2021. DOI: https://doi.org/10.1109/JSEN.2019.2923982
[5] M. Sui, C. Zhang, L. Zhou, S. Liao and C. Wei, "An Ensemble Approach to Stock Price Prediction Using Deep Learning and Time Series Models," 2024 IEEE 6th International Conference on Power, Intelligent Computing and Systems (ICPICS), Shenyang, China, 2024, pp. 793-797. DOI: https://doi.org/10.1109/ICPICS62053.2024.10796661
[6] Almutairi E, Abbod M, Hunaiti Z. Prediction of diabetes using statistical and machine learning modelling techniques[J]. Algorithms, 2025, 18: 145. DOI: https://doi.org/10.3390/a18030145
[7] Khedr A, Arif I, P V PR, et al. Cryptocurrency price prediction using traditional statistical and machine learning techniques: A survey[J]. Intelligent Systems in Accounting, Finance and Management, 2021, 28(1): 3-34. DOI: https://doi.org/10.1002/isaf.1488
[8] Yao Z, Su J N, Fan G, et al. GACA: a gradient-aware and contrastive-adaptive learning framework for low-light image enhancement[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 1-14. DOI: https://doi.org/10.1109/TIM.2024.3353285
[9] LI Yuyao, ZHANG Xiangwen, LI Ziyang, et al. Accurate and adaptive state of health estimation for lithium-ion battery based on patch learning framework[J]. Measurement, 2025, 250: 117083. DOI: https://doi.org/10.1016/j.measurement.2025.117083
[10] LIU Haoxin, XU Shangqing, ZHAO Zhiyuan, et al. Time-MMD: multi-domain multimodal dataset for time series analysis[C]//GLOBERSON A, MACKEY L, BELGRAVE D, et al. Advances in Neural Information Processing Systems. New York: Curran Associates, Inc., 2024: 77888-77933. DOI: https://doi.org/10.52202/079017-2476
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Transactions on Computer Science and Intelligent Systems Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
