Brain imaging and forecasting: Insights from judgmental model selection

Weiwei Han, Xun Wang, Fotios Petropoulos, Jing Wang

Research output: Contribution to journalArticle

Abstract

In this article, we shed light on the differences between two judgmental forecasting approaches for model selection – forecast selection and pattern identification – with regard to their forecasting performance and underlying cognitive processes. We designed a laboratory experiment using real-life time series as stimuli to record subjects’ selections as well as their brain activity by means of electroencephalography (EEG). We found that their cognitive load, measured by the amplitude of parietal P300, can be effectively used as a neurological indicator of identification and forecast accuracy. As a result, judgmental forecasting based on pattern identification outperforms forecast selection. Time series with low trendiness and noisiness have low forecasting accuracy because of the high cognitive load induced.
LanguageEnglish
JournalOmega: The International Journal of Management Science
Early online date16 Nov 2018
DOIs
StatusE-pub ahead of print - 16 Nov 2018

Cite this

Brain imaging and forecasting: Insights from judgmental model selection. / Han, Weiwei; Wang, Xun; Petropoulos, Fotios; Wang, Jing.

In: Omega: The International Journal of Management Science, 16.11.2018.

Research output: Contribution to journalArticle

@article{bdb27b65630544adb77bcdbea9ee91e6,
title = "Brain imaging and forecasting: Insights from judgmental model selection",
abstract = "In this article, we shed light on the differences between two judgmental forecasting approaches for model selection – forecast selection and pattern identification – with regard to their forecasting performance and underlying cognitive processes. We designed a laboratory experiment using real-life time series as stimuli to record subjects’ selections as well as their brain activity by means of electroencephalography (EEG). We found that their cognitive load, measured by the amplitude of parietal P300, can be effectively used as a neurological indicator of identification and forecast accuracy. As a result, judgmental forecasting based on pattern identification outperforms forecast selection. Time series with low trendiness and noisiness have low forecasting accuracy because of the high cognitive load induced.",
author = "Weiwei Han and Xun Wang and Fotios Petropoulos and Jing Wang",
year = "2018",
month = "11",
day = "16",
doi = "10.1016/j.omega.2018.11.015",
language = "English",
journal = "Omega: The International Journal of Management Science",

}

TY - JOUR

T1 - Brain imaging and forecasting: Insights from judgmental model selection

AU - Han, Weiwei

AU - Wang, Xun

AU - Petropoulos, Fotios

AU - Wang, Jing

PY - 2018/11/16

Y1 - 2018/11/16

N2 - In this article, we shed light on the differences between two judgmental forecasting approaches for model selection – forecast selection and pattern identification – with regard to their forecasting performance and underlying cognitive processes. We designed a laboratory experiment using real-life time series as stimuli to record subjects’ selections as well as their brain activity by means of electroencephalography (EEG). We found that their cognitive load, measured by the amplitude of parietal P300, can be effectively used as a neurological indicator of identification and forecast accuracy. As a result, judgmental forecasting based on pattern identification outperforms forecast selection. Time series with low trendiness and noisiness have low forecasting accuracy because of the high cognitive load induced.

AB - In this article, we shed light on the differences between two judgmental forecasting approaches for model selection – forecast selection and pattern identification – with regard to their forecasting performance and underlying cognitive processes. We designed a laboratory experiment using real-life time series as stimuli to record subjects’ selections as well as their brain activity by means of electroencephalography (EEG). We found that their cognitive load, measured by the amplitude of parietal P300, can be effectively used as a neurological indicator of identification and forecast accuracy. As a result, judgmental forecasting based on pattern identification outperforms forecast selection. Time series with low trendiness and noisiness have low forecasting accuracy because of the high cognitive load induced.

U2 - 10.1016/j.omega.2018.11.015

DO - 10.1016/j.omega.2018.11.015

M3 - Article

JO - Omega: The International Journal of Management Science

T2 - Omega: The International Journal of Management Science

JF - Omega: The International Journal of Management Science

ER -