A “Softer” Approach to the Measurement of Forecast Accuracy

John Boylan

Foresight: The International Journal of Applied Forecasting, 2011, issue 23, 16-20

Abstract: Foresight’s Summer 2010 issue contained a letter to the editor from David Hawitt, suggesting that forecast managers would be more receptive to hearing about forecast accuracy rather than forecast error. If forecast error is measured by the average absolute percentage error (MAPE), then forecast accuracy would be the complement, 100% - MAPE. David argued that while reporting (e.g.) a 40% average error might generate “knee-jerk reactions and the creation of unrealistic goals,” reporting 60% accuracy stimulates executive thinking about “What can we do to improve this?” Then, in the Spring 2011 issue of Foresight, Mark Little and Jim Hoover offered their commentaries on the Hawitt recommendation. Mark had a different take on the issue: “Rather than attempt to express accuracy in a form executives think they understand, it may be better to focus on the improvements in business outcomes (the KPIs) that result through better forecasts.” The issue was carried forward in recent Linked-In exchanges, which John Boylan mentions below in his reflections. John sees the discussion in terms of the different perspectives of academics and practitioners, and attempts to reconcile these positions through the lens of Soft Systems Methodology. Copyright International Institute of Forecasters, 2011

Date: 2011
References: Add references at CitEc
Citations:

Downloads: (external link)
https://foresight.forecasters.org/shop/

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:for:ijafaa:y:2011:i:23:p:16-20

Access Statistics for this article

More articles in Foresight: The International Journal of Applied Forecasting from International Institute of Forecasters Contact information at EDIRC.
Bibliographic data for series maintained by Michael Gilliland ().