Home > Research > Publications & Outputs > The accuracy of intermittent demand estimates
View graph of relations

The accuracy of intermittent demand estimates

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

The accuracy of intermittent demand estimates. / Syntetos, Aris A.; Boylan, John.

In: International Journal of Forecasting, Vol. 21, No. 2, 01.04.2005, p. 303-314.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Syntetos, AA & Boylan, J 2005, 'The accuracy of intermittent demand estimates', International Journal of Forecasting, vol. 21, no. 2, pp. 303-314. https://doi.org/10.1016/j.ijforecast.2004.10.001

APA

Syntetos, A. A., & Boylan, J. (2005). The accuracy of intermittent demand estimates. International Journal of Forecasting, 21(2), 303-314. https://doi.org/10.1016/j.ijforecast.2004.10.001

Vancouver

Syntetos AA, Boylan J. The accuracy of intermittent demand estimates. International Journal of Forecasting. 2005 Apr 1;21(2):303-314. doi: 10.1016/j.ijforecast.2004.10.001

Author

Syntetos, Aris A. ; Boylan, John. / The accuracy of intermittent demand estimates. In: International Journal of Forecasting. 2005 ; Vol. 21, No. 2. pp. 303-314.

Bibtex

@article{15e21e71fc8e4f6d9688613e2b71aeff,
title = "The accuracy of intermittent demand estimates",
abstract = "Intermittent demand appears sporadically, with some time periods showing no demand at all. In this paper, four forecasting methods, Simple Moving Average (SMA, 13 periods), Single Exponential Smoothing (SES), Croston's method, and a new method (based on Croston's approach) recently developed by the authors, are compared on 3000 real intermittent demand data series from the automotive industry. The mean signed and relative geometric root-mean-square errors are shown to meet the theoretical and practical requirements of intermittent demand, as do the Percentage Better and Percentage Best summary statistics based on these measures. These measures are subsequently applied in a simulation experiment. The out-of-sample comparison results indicate superior performance of the new method. In addition, the results show that the mean signed error is not strongly scale dependent and the relative geometric root-mean-square error is a well-behaved accuracy measure for intermittent demand.",
keywords = "Demand forcasting, Intermittent demand, Accuracy measures, Croston's method, Exponential smoothing, Forcasting competition",
author = "Syntetos, {Aris A.} and John Boylan",
year = "2005",
month = apr,
day = "1",
doi = "10.1016/j.ijforecast.2004.10.001",
language = "English",
volume = "21",
pages = "303--314",
journal = "International Journal of Forecasting",
issn = "0169-2070",
publisher = "Elsevier Science B.V.",
number = "2",

}

RIS

TY - JOUR

T1 - The accuracy of intermittent demand estimates

AU - Syntetos, Aris A.

AU - Boylan, John

PY - 2005/4/1

Y1 - 2005/4/1

N2 - Intermittent demand appears sporadically, with some time periods showing no demand at all. In this paper, four forecasting methods, Simple Moving Average (SMA, 13 periods), Single Exponential Smoothing (SES), Croston's method, and a new method (based on Croston's approach) recently developed by the authors, are compared on 3000 real intermittent demand data series from the automotive industry. The mean signed and relative geometric root-mean-square errors are shown to meet the theoretical and practical requirements of intermittent demand, as do the Percentage Better and Percentage Best summary statistics based on these measures. These measures are subsequently applied in a simulation experiment. The out-of-sample comparison results indicate superior performance of the new method. In addition, the results show that the mean signed error is not strongly scale dependent and the relative geometric root-mean-square error is a well-behaved accuracy measure for intermittent demand.

AB - Intermittent demand appears sporadically, with some time periods showing no demand at all. In this paper, four forecasting methods, Simple Moving Average (SMA, 13 periods), Single Exponential Smoothing (SES), Croston's method, and a new method (based on Croston's approach) recently developed by the authors, are compared on 3000 real intermittent demand data series from the automotive industry. The mean signed and relative geometric root-mean-square errors are shown to meet the theoretical and practical requirements of intermittent demand, as do the Percentage Better and Percentage Best summary statistics based on these measures. These measures are subsequently applied in a simulation experiment. The out-of-sample comparison results indicate superior performance of the new method. In addition, the results show that the mean signed error is not strongly scale dependent and the relative geometric root-mean-square error is a well-behaved accuracy measure for intermittent demand.

KW - Demand forcasting

KW - Intermittent demand

KW - Accuracy measures

KW - Croston's method

KW - Exponential smoothing

KW - Forcasting competition

U2 - 10.1016/j.ijforecast.2004.10.001

DO - 10.1016/j.ijforecast.2004.10.001

M3 - Journal article

VL - 21

SP - 303

EP - 314

JO - International Journal of Forecasting

JF - International Journal of Forecasting

SN - 0169-2070

IS - 2

ER -