Shrinkage Estimator for Exponential Smoothing Models

Pritularga, Kandrika and Svetunkov, Ivan and Kourentzes, Nikolaos (2022) Shrinkage Estimator for Exponential Smoothing Models. International Journal of Forecasting. pp. 1-15. ISSN 0169-2070

[img]
Text (Pure_Shrinkage_Estimator_for_Exponential_Smoothing_Models)
Pure_Shrinkage_Estimator_for_Exponential_Smoothing_Models.pdf - Accepted Version
Restricted to Repository staff only until 12 August 2024.
Available under License Creative Commons Attribution-NonCommercial-NoDerivs.

Download (479kB)

Abstract

Exponential smoothing is widely used in practice and has shown its efficacy and reliability in many business applications. Yet there are cases, for example when the estimation sample is limited, where the estimated smoothing parameters can be erroneous, often unnecessarily large. This can lead to over-reactive forecasts and high forecast errors. Motivated by these challenges, we investigate the use of shrinkage estimators for exponential smoothing. This can help with parameter estimation and mitigating parameter uncertainty. Building on the shrinkage literature, we explore ℓ 1 and ℓ 2 shrinkage for different time series and exponential smoothing model specifications. From a simulation and an empirical study, we find that using shrinkage in exponential smoothing results in forecast accuracy improvements and better prediction intervals. In addition, using bias–variance decomposition, we show the interdependence between smoothing parameters and initial values, and the importance of the initial value estimation on point forecasts and prediction intervals.

Item Type:
Journal Article
Journal or Publication Title:
International Journal of Forecasting
Additional Information:
This is the author’s version of a work that was accepted for publication in International Journal of Forecasting. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in International Journal of Forecasting, Vol., pages, 2022 DOI: 110.1016/j.ijforecast.2022.07.005
Uncontrolled Keywords:
Data Sharing Template/no
Subjects:
ID Code:
175569
Deposited By:
Deposited On:
06 Sep 2022 14:55
Refereed?:
Yes
Published?:
Published
Last Modified:
22 Nov 2022 11:47