Forecasting performance of machine learning, time series, and hybrid methods for low- and high-frequency time series
Published in Statistica Neerlandica, 2023
Recommended citation: Özdemir, O., & Yozgatlıgil, C. (2023). Forecasting performance of machine learning, time series, and hybrid methods for low- and high-frequency time series. Statistica Neerlandica. https://doi.org/10.1111/stan.12326 https://onlinelibrary.wiley.com/doi/10.1111/stan.12326
Overview
This article compares the forecasting performance of machine learning, classical time series, and hybrid methods across low- and high-frequency time series. It contributes to the practical evaluation of forecasting models by examining how different methodological families perform under varying temporal structures and data frequencies.
Citation
Özdemir, O., & Yozgatlıgil, C. (2023). Forecasting performance of machine learning, time series, and hybrid methods for low- and high-frequency time series. Statistica Neerlandica. https://doi.org/10.1111/stan.12326