RT Journal Article
T1 A New Predictive Algorithm for Time Series Forecasting Based on Machine Learning Techniques: Evidence for Decision Making in Agriculture and Tourism Sectors
A1 Borrero Sánchez, Juan Diego
A1 Mariscal, Jesús
A1 Vargas Sánchez, Alfonso
AB Accurate time series prediction techniques are becoming fundamental to modern decisionsupport systems. As massive data processing develops in its practicality, machine learning (ML)techniques applied to time series can automate and improve prediction models. The radical noveltyof this paper is the development of a hybrid model that combines a new approach to the classicalKalman filter with machine learning techniques, i.e., support vector regression (SVR) and nonlinearautoregressive (NAR) neural networks, to improve the performance of existing predictive models.The proposed hybrid model uses, on the one hand, an improved Kalman filter method that eliminatesthe convergence problems of time series data with large error variance and, on the other hand, an MLalgorithm as a correction factor to predict the model error. The results reveal that our hybrid modelsobtain accurate predictions, substantially reducing the root mean square and absolute mean errorscompared to the classical and alternative Kalman filter models and achieving a goodness of fit greaterthan 0.95. Furthermore, the generalization of this algorithm was confirmed by its validation in twodifferent scenarios
PB MDPI
SN 2571-905X (electrónico)
YR 2022
FD 2022-11
LK https://hdl.handle.net/10272/21587
UL https://hdl.handle.net/10272/21587
LA eng
NO Borrero, J. D., Mariscal, J., & Vargas-Sánchez, A. (2022). A New Predictive Algorithm for Time Series Forecasting Based on Machine Learning Techniques: Evidence for Decision Making in Agriculture and Tourism Sectors. In Stats (Vol. 5, Issue 4, pp. 1145–1158). MDPI AG. https://doi.org/10.3390/stats5040068
NO The authors acknowledge the support provided by the companies that releasedthe data used for the analysis
DS Repositorio Institucional de la Universidad de Huelva
RD 31 may 2026