Abstract
To compare different forecasting methods on demand series, we require an error measure. Many error measures have been proposed, but when demand is intermittent some become inapplicable because of infinities, some give counter-intuitive results, and there is no agreement on which is best. We argue that almost all known measures rank forecasters incorrectly on intermittent demand series. We propose several new error measures with almost no infinities, and with correct forecaster ranking on several intermittent demand patterns. We call these ‘mean-based’ error measures because they evaluate forecasts against the (possibly time-dependent) mean of the underlying stochastic process instead of point demands.
Notes
This work was partially funded by Enterprise Ireland Innovation Voucher IV-2009-2092. S. Armagan Tarim is supported by the Scientific and Technological Research Council of Turkey (TUBITAK) under [grant number 110M500]. R. Rossi is supported by the University of Edinburgh CHSS Challenge Investment Fund and by the European Community’s Seventh Framework Programme (FP7) under [grant number 244994] (project VEG-i-TRADE).