A state space framework for automatic forecasting using exponential smoothing methods

A new approach to automatic forecasting based on an extended range of exponential smoothing methods is provided. Each method in the taxonomy of exponential smoothing methods provides forecasts that are equivalent to forecast from a state based model. This equivalence allows: 1. easy calculation of t...

Full description

Saved in:
Bibliographic Details
Published in:International journal of forecasting 2002-07, Vol.18 (3), p.439-454
Main Authors: Hyndman, Rob J, Grose, Simone, Koehler, Anne B, Snyder, Ralph David
Format: Article
Language:English
Subjects:
Accuracy
Economic forecasting
Economic models
Forecasting techniques
Studies
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A new approach to automatic forecasting based on an extended range of exponential smoothing methods is provided. Each method in the taxonomy of exponential smoothing methods provides forecasts that are equivalent to forecast from a state based model. This equivalence allows: 1. easy calculation of the likelihood, the AIC and other model selection criteria, 2. computation of prediction intervals for each method, and 3. random simulation from the underlying state space model. The methods are demonstrated by applying them to the data from the M-competition and M3-competition. The method provides forecast accuracy comparable to the best methods in the competitions; it is particularly good for short forecast horizons with seasonal data.
ISSN:0169-2070
1872-8200
DOI:10.1016/s0169-2070(01)00110-8