Automatic robust estimation for exponential smoothing: Perspectives from statistics and machine learning

Barrow, DevonBirmingham Business School Department of Management, United Kingdom,University of Birmingham (GB) (författare)

Automatic robust estimation for exponential smoothing : Perspectives from statistics and machine learning

LIBRIS-ID:oai:DiVA.org:his-18482
https://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-18482URI
https://doi.org/10.1016/j.eswa.2020.113637DOI
https://research.hhs.se/esploro/outputs/journalArticle/Automatic-robust-estimation-for-exponential-smoothing/991001480541906056URI

A major challenge in automating the production of a large number of forecasts, as often required in many business applications, is the need for robust and reliable predictions. Increased noise, outliers and structural changes in the series, all too common in practice, can severely affect the quality of forecasting. We investigate ways to increase the reliability of exponential smoothing forecasts, the most widely used family of forecasting models in business forecasting. We consider two alternative sets of approaches, one stemming from statistics and one from machine learning. To this end, we adapt M-estimators, boosting and inverse boosting to parameter estimation for exponential smoothing. We propose appropriate modifications that are necessary for time series forecasting while aiming to obtain scalable algorithms. We evaluate the various estimation methods using multiple real datasets and find that several approaches outperform the widely used maximum likelihood estimation. The novelty of this work lies in (1) demonstrating the usefulness of M-estimators, (2) and of inverse boosting, which outperforms standard boosting approaches, and (3) a comparative look at statistics versus machine learning inspired approaches.

Kourentzes, NikolaosHögskolan i Skövde,Institutionen för informationsteknologi,Forskningsmiljön Informationsteknologi,Lancaster University Management School Department of Management Science, United Kingdom,Skövde Artificial Intelligence Lab (SAIL),University of Skövde (SE)(Swepub:his)koun (författare)
Sandberg, RickardStockholm School of Economics,Handelshögskolan i Stockholm(Swepub:hhs)356@hhs.se (författare)
Niklewski, JacekCoventry University Faculty of Business, Environment and Society, United Kingdom,Coventry University (författare)
Birmingham Business School Department of Management, United KingdomUniversity of Birmingham (GB) (creator_code:org_t)

Av författaren/redakt...: Barrow, Devon; Kourentzes, Niko ...; Sandberg, Rickar ...; Niklewski, Jacek

Om ämnet

SAMHÄLLSVETENSKAP: SAMHÄLLSVETENSKA ...; och Ekonomi och näri ...; och Nationalekonomi

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Samhällsbyggnads ...; och Transportteknik ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.