Forecasting when pattern changes occur beyond the historical data

Robert Carbone, Spyros Makridakis

    Research output: Contribution to journalArticlepeer-review

    26 Citations (Scopus)

    Abstract

    Forecasting methods currently available assume that established patterns or relationships will not change during the post-sample forecasting phase. This, however, is not a realistic assumption for business and economic series. This paper describes a new approach to forecasting which takes into account possible pattern changes beyond the histoncal data. This approach is based on the development of two models: one short, the other long term. These models are then reconciled to produce the final forecasts by setting certain parameters as a function of the number, extent, and duration of pattern changes that have occurred in the past. The proposed method has been applied to the 111 series used in the M-Competition. Post-sample forecasting accuracy compansons show the superiority of the proposed approach over the most accurate methods in the A/-Competition.

    Original languageEnglish
    Pages (from-to)257-271
    Number of pages15
    JournalManagement Science
    Volume32
    Issue number3
    Publication statusPublished - 1 Mar 1986

    Fingerprint

    Dive into the research topics of 'Forecasting when pattern changes occur beyond the historical data'. Together they form a unique fingerprint.

    Cite this