Multi-Series Heuristics for Exponential Smoothing

In this paper several heuristics are proposed for calculating the smoothing parameter in exponential smoothing when forecasts of many 'closely' related series are required on a regular basis. The methods are evaluated using both synthetic and real data. They not only compare favourably against several other known forecasting techniques but they are also simple and computationally efficient.


Issue Date:
Jan 01 1989
Publication Type:
Working or Discussion Paper
Language:
English
Total Pages:
23
Series Statement:
Working Paper No. 1/89




 Record created 2018-01-22, last modified 2018-01-23

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)