Classification and regression tree approach for the prediction of the seasonal apparel market: focused on weather factors
Journal of Fashion Marketing and Management
ISSN: 1361-2026
Article publication date: 22 December 2023
Abstract
Purpose
Climate change-induced weather changes are severe and frequent, making it difficult to predict apparel sales. The primary goal of this study was to assess consumers' responses to winter apparel searches when external stimuli, such as weather, calendars and promotions arise and to develop a decision-making tool that allows apparel retailers to establish sales strategies according to external stimuli.
Design/methodology/approach
The theoretical framework of this study was the effect of external stimuli, such as calendar, promotion and weather, on seasonal apparel search in a consumer's decision-making process. Using weather observation data and Google Trends over the past 12 years, from 2008 to 2020, consumers' responses to external stimuli were analyzed using a classification and regression tree to gain consumer insights into the decision process. The relative importance of the factors in the model was determined, a tree model was developed and the model was tested.
Findings
Winter apparel searches increased when the average, maximum and minimum temperatures, windchill, and the previous day's windchill decreased. The month of the year varies depending on weather factors, and promotional sales events do not increase search activities for seasonal apparel. However, sales events during the higher-than-normal temperature season triggered search activity for seasonal apparel.
Originality/value
Consumer responses to external stimuli were analyzed through classification and regression trees to discover consumer insights into the decision-making process to improve stock management because climate change-induced weather changes are unpredictable.
Keywords
Acknowledgements
Funding: This work was supported by the Ministry of Education of the Republic of Korea and the National Research Foundation of Korea (NRF-2021S1A5B5A16077490).
Erratum: It has come to the attention of the publisher that the article, Oh, J. (2023), “Classification and regression tree approach for the prediction of the seasonal apparel market: focused on weather factors”, Journal of Fashion Marketing and Management, Vol. ahead-of-print No. ahead-of-print. https://doi.org/10.1108/JFMM-12-2022-0266, was published with a text error in the Introduction section. This error was introduced in the production process and has now been corrected in the online version. The publisher sincerely apologises for this error and for any inconvenience caused.
Citation
Oh, J. (2023), "Classification and regression tree approach for the prediction of the seasonal apparel market: focused on weather factors", Journal of Fashion Marketing and Management, Vol. ahead-of-print No. ahead-of-print. https://doi.org/10.1108/JFMM-12-2022-0266
Publisher
:Emerald Publishing Limited
Copyright © 2023, Emerald Publishing Limited