Nonlinear forecasting with many predictors using mixed data sampling kernel ridge regression models
(2025) In Annals of Operations Research- Abstract
Policy institutes such as central banks need accurate forecasts of key measures of economic activity to design stabilization policies that reduce the severity of economic fluctuations. Therefore, this paper develops a kernel ridge regression estimator in a mixed data sampling framework. Kernel ridge regression can handle many predictors with a nonlinear relationship to the target variable. Consequently, it has potential to improve the currently used principal component-based methods when the economic data follow a nonlinear factor structure. In a Monte Carlo study, we show that the kernel ridge regression approach is superior in terms of mean square error and is more robust than principal component-based methods to different nonlinear... (More)
Policy institutes such as central banks need accurate forecasts of key measures of economic activity to design stabilization policies that reduce the severity of economic fluctuations. Therefore, this paper develops a kernel ridge regression estimator in a mixed data sampling framework. Kernel ridge regression can handle many predictors with a nonlinear relationship to the target variable. Consequently, it has potential to improve the currently used principal component-based methods when the economic data follow a nonlinear factor structure. In a Monte Carlo study, we show that the kernel ridge regression approach is superior in terms of mean square error and is more robust than principal component-based methods to different nonlinear data generating processes. By using a dataset consisting of 24 economic indicators, we forecast Swedish gross domestic production. The results confirm the superiority of the kernel ridge regression approach. Therefore, we suggest that policy institutes consider the use of kernel-based approaches when forecasting key measures of economic activity.
(Less)
- author
- Dai, Deliang ; Javed, Farrukh LU ; Karlsson, Peter and Månsson, Kristofer
- organization
- publishing date
- 2025
- type
- Contribution to journal
- publication status
- epub
- subject
- keywords
- Big data, Forecasting, Kernel ridge regression, MIDAS
- in
- Annals of Operations Research
- publisher
- Springer
- external identifiers
-
- scopus:85217421712
- ISSN
- 0254-5330
- DOI
- 10.1007/s10479-025-06486-y
- language
- English
- LU publication?
- yes
- id
- c0a81d7b-33a8-4755-acef-30f77c40ff24
- date added to LUP
- 2025-06-02 09:32:38
- date last changed
- 2025-06-02 09:33:46
@article{c0a81d7b-33a8-4755-acef-30f77c40ff24,
abstract = {{<p>Policy institutes such as central banks need accurate forecasts of key measures of economic activity to design stabilization policies that reduce the severity of economic fluctuations. Therefore, this paper develops a kernel ridge regression estimator in a mixed data sampling framework. Kernel ridge regression can handle many predictors with a nonlinear relationship to the target variable. Consequently, it has potential to improve the currently used principal component-based methods when the economic data follow a nonlinear factor structure. In a Monte Carlo study, we show that the kernel ridge regression approach is superior in terms of mean square error and is more robust than principal component-based methods to different nonlinear data generating processes. By using a dataset consisting of 24 economic indicators, we forecast Swedish gross domestic production. The results confirm the superiority of the kernel ridge regression approach. Therefore, we suggest that policy institutes consider the use of kernel-based approaches when forecasting key measures of economic activity.</p>}},
author = {{Dai, Deliang and Javed, Farrukh and Karlsson, Peter and Månsson, Kristofer}},
issn = {{0254-5330}},
keywords = {{Big data; Forecasting; Kernel ridge regression; MIDAS}},
language = {{eng}},
publisher = {{Springer}},
series = {{Annals of Operations Research}},
title = {{Nonlinear forecasting with many predictors using mixed data sampling kernel ridge regression models}},
url = {{http://dx.doi.org/10.1007/s10479-025-06486-y}},
doi = {{10.1007/s10479-025-06486-y}},
year = {{2025}},
}