An Improved ARIMA-Neural Network Fusion Model for Multivariate Time-Series Prediction with External Factor Integration
DOI:
https://doi.org/10.62051/haq1rt76Keywords:
ARIMA Model; Neural Network; Bayesian theory; Fusion Model.Abstract
This study aims to solve the difficult problem of sports performance prediction and improve the accuracy and reliability of prediction. The improved ARIMA and neural network fusion technology was used to clean and standardize the sports data first, and then the improved ARIMA model was used to capture the time series features, and external factors such as athletes' physical fitness and training level were included in the model, and special cases were predicted by combining Bayes theory. Finally, neural network is used to further optimize the prediction results. The experimental results show that the fusion technology effectively integrates the advantages of the two models, and the prediction error is significantly reduced compared with the single model. The research conclusion is that the improved ARIMA and neural network fusion technology is feasible and effective in the field of sports performance prediction, which provides an innovative method for subsequent sports-related research and practice, and strongly promotes the development of sports data prediction technology.
Downloads
References
[1] Wang J, Liu Y, Li Y. A parallel differential learning ensemble framework based on enhanced feature extraction and anti-information leakage mechanism for ultra-short-term wind speed forecast[J].Applied Energy,2024,361122909-. DOI: https://doi.org/10.1016/j.apenergy.2024.122909
[2] He N ,Yang Z ,Qian C , et al.Remaining useful life prediction of lithium-ion battery based on fusion model considering capacity regeneration phenomenon[J].Journal of Energy Storage,2024,85111068-. DOI: https://doi.org/10.1016/j.est.2024.111068
[3] Grasa R P, Rodriguez F R, Novelli G, et al. Satellite image classification with neural quantum kernels[J]. Machine Learning: Science and Technology,2025,6(1):015043-015043. DOI: https://doi.org/10.1088/2632-2153/ada86c
[4] Hashemi A, Izadkhah A. A graph neural network simulation of dispersed systems[J].Machine Learning: Science and Technology,2025,6(1):015044-015044. DOI: https://doi.org/10.1088/2632-2153/adb0a0
[5] Wang T, Tan X, Tian Y, et al. Risk assessment based on Bayesian Network for the typhoon-storm surge-flood-dike burst disaster chain: A case study of Guangdong, China[J]. Journal of Hydrology: Regional Studies,2025,58102251-102251. DOI: https://doi.org/10.2139/ssrn.4890445
[6] Zheng R ,Yang B ,Qian Y , et al.Joint SOH and RUL estimation for lithium-ion batteries via optimal deep belief network with Bayesian algorithm[J].Journal of Energy Storage,2025,114(PB):115891-115891. DOI: https://doi.org/10.1016/j.est.2025.115891
[7] Wang Y, Yan L, Zhou T. Deep learning-enhanced reduced-order ensemble Kalman filter for efficient Bayesian data assimilation of parametric PDEs[J]. Computer Physics Communications,2025,311109544-109544. DOI: https://doi.org/10.1016/j.cpc.2025.109544
[8] Sepehry N ,Ehsani M ,Amindavar H , et al.A novel enhanced Superlet Synchroextracting transform ensemble learning for structural health monitoring using nonlinear wave modulation[J].Engineering Applications of Artificial Intelligence,2025,147110341-110341. DOI: https://doi.org/10.1016/j.engappai.2025.110341
[9] Shen S, Cheng J, Liu Z, et al. Bayesian inference-assisted reliability analysis framework for robotic motion systems in future factories[J]. Reliability Engineering and System Safety,2025,258110894-110894. DOI: https://doi.org/10.1016/j.ress.2025.110894
[10] Zhang Y, Liu L, Qiao Q, et al. A Lie group Laplacian Support Vector Machine for semi-supervised learning[J]. Neurocomputing,2025,630129728-129728. DOI: https://doi.org/10.2139/ssrn.4870746
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.
