Judgmental Selection of Forecasting Models (Reprint)

Fotios Petropoulos; Nikolaos Kourentzes; Konstantinos Nikolopoulos; Enno Siemsen

doi:10.1007/978-3-031-30085-1_3

Judgmental Selection of Forecasting Models (Reprint)

Fotios Petropoulos, Nikolaos Kourentzes, Konstantinos Nikolopoulos, Enno Siemsen

Research output: Chapter or section in a book/report/conference proceeding › Chapter or section

Abstract

In this paper, we explored how judgment can be used to improve the selection of a forecasting model. We compared the performance of judgmental model selection against a standard algorithm based on information criteria. We also examined the efficacy of a judgmental model-build approach, in which experts were asked to decide on the existence of the structural components (trend and seasonality) of the time series instead of directly selecting a model from a choice set. Our behavioral study used data from almost 700 participants, including forecasting practitioners. The results from our experiment suggest that selecting models judgmentally results in performance that is on par, if not better, to that of algorithmic selection. Further, judgmental model selection helps to avoid the worst models more frequently compared to algorithmic selection. Finally, a simple combination of the statistical and judgmental selections and judgmental aggregation significantly outperform both statistical and judgmental selections.

Original language	English
Title of host publication	Judgment in Predictive Analytics
Editors	M. Seifert
Place of Publication	Cham, Switzerland
Publisher	Springer
Pages	53-84
Number of pages	32
ISBN (Electronic)	9783031300851
ISBN (Print)	9783031300844
DOIs	https://doi.org/10.1007/978-3-031-30085-1_3
Publication status	Published - 3 Jun 2023

Publication series

Name	International Series in Operations Research and Management Science
Volume	343
ISSN (Print)	0884-8289
ISSN (Electronic)	2214-7934

Funding

Acknowledgments FP and NK would like to acknowledge the support for conducting this research provided by the Lancaster University Management School Early Career Research Grant MTA7690.

Keywords

Behavioral operations
Combination
Decomposition
Judgmental forecasting
Model selection

ASJC Scopus subject areas

Software
Computer Science Applications
Strategy and Management
Management Science and Operations Research
Applied Mathematics

Access to Document

10.1007/978-3-031-30085-1_3

Cite this

Judgmental Selection of Forecasting Models (Reprint). / Petropoulos, Fotios; Kourentzes, Nikolaos; Nikolopoulos, Konstantinos et al.
Judgment in Predictive Analytics. ed. / M. Seifert. Cham, Switzerland: Springer, 2023. p. 53-84 (International Series in Operations Research and Management Science; Vol. 343).

Research output: Chapter or section in a book/report/conference proceeding › Chapter or section

@inbook{65d2300227234b12b9ee4d326082e0a1,

title = "Judgmental Selection of Forecasting Models (Reprint)",

abstract = "In this paper, we explored how judgment can be used to improve the selection of a forecasting model. We compared the performance of judgmental model selection against a standard algorithm based on information criteria. We also examined the efficacy of a judgmental model-build approach, in which experts were asked to decide on the existence of the structural components (trend and seasonality) of the time series instead of directly selecting a model from a choice set. Our behavioral study used data from almost 700 participants, including forecasting practitioners. The results from our experiment suggest that selecting models judgmentally results in performance that is on par, if not better, to that of algorithmic selection. Further, judgmental model selection helps to avoid the worst models more frequently compared to algorithmic selection. Finally, a simple combination of the statistical and judgmental selections and judgmental aggregation significantly outperform both statistical and judgmental selections.",

keywords = "Behavioral operations, Combination, Decomposition, Judgmental forecasting, Model selection",

author = "Fotios Petropoulos and Nikolaos Kourentzes and Konstantinos Nikolopoulos and Enno Siemsen",

year = "2023",

month = jun,

day = "3",

doi = "10.1007/978-3-031-30085-1_3",

language = "English",

isbn = "9783031300844",

series = "International Series in Operations Research and Management Science",

publisher = "Springer",

pages = "53--84",

editor = "M. Seifert",

booktitle = "Judgment in Predictive Analytics",

}

TY - CHAP

T1 - Judgmental Selection of Forecasting Models (Reprint)

AU - Petropoulos, Fotios

AU - Kourentzes, Nikolaos

AU - Nikolopoulos, Konstantinos

AU - Siemsen, Enno

PY - 2023/6/3

Y1 - 2023/6/3

N2 - In this paper, we explored how judgment can be used to improve the selection of a forecasting model. We compared the performance of judgmental model selection against a standard algorithm based on information criteria. We also examined the efficacy of a judgmental model-build approach, in which experts were asked to decide on the existence of the structural components (trend and seasonality) of the time series instead of directly selecting a model from a choice set. Our behavioral study used data from almost 700 participants, including forecasting practitioners. The results from our experiment suggest that selecting models judgmentally results in performance that is on par, if not better, to that of algorithmic selection. Further, judgmental model selection helps to avoid the worst models more frequently compared to algorithmic selection. Finally, a simple combination of the statistical and judgmental selections and judgmental aggregation significantly outperform both statistical and judgmental selections.

AB - In this paper, we explored how judgment can be used to improve the selection of a forecasting model. We compared the performance of judgmental model selection against a standard algorithm based on information criteria. We also examined the efficacy of a judgmental model-build approach, in which experts were asked to decide on the existence of the structural components (trend and seasonality) of the time series instead of directly selecting a model from a choice set. Our behavioral study used data from almost 700 participants, including forecasting practitioners. The results from our experiment suggest that selecting models judgmentally results in performance that is on par, if not better, to that of algorithmic selection. Further, judgmental model selection helps to avoid the worst models more frequently compared to algorithmic selection. Finally, a simple combination of the statistical and judgmental selections and judgmental aggregation significantly outperform both statistical and judgmental selections.

KW - Behavioral operations

KW - Combination

KW - Decomposition

KW - Judgmental forecasting

KW - Model selection

UR - http://www.scopus.com/inward/record.url?scp=85162055731&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-30085-1_3

DO - 10.1007/978-3-031-30085-1_3

M3 - Chapter or section

AN - SCOPUS:85162055731

SN - 9783031300844

T3 - International Series in Operations Research and Management Science

SP - 53

EP - 84

BT - Judgment in Predictive Analytics

A2 - Seifert, M.

PB - Springer

CY - Cham, Switzerland

ER -

Judgmental Selection of Forecasting Models (Reprint)

Abstract

Publication series

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this