Classification of commercial districts based on predicting the survival rate of food service market in Seoul
DongHyeon Lee,
Jaekyung Lee,
ManSu Kang and
SangHyun Cheon
PLOS ONE, 2025, vol. 20, issue 7, 1-23
Abstract:
The chronic small-business closure has emerged as a critical economic issue in South Korea, considering more than half of businesses have been closed within three years. While some previous literature has analyzed the causes and their negative impacts on the economy, there is still a lack of studies on understanding the pattern dynamics and predicting future possible closure scenarios due to the lack of appropriate data. Using 3,000,000 individual commercial facility data from 2004 to 2018 in Seoul, Korea, the primary purpose of this research is two-fold: (1) to develop a methodological framework to simulate survival rate pattern change using a deep-learning based model and (2) to reclassify the commercial districts based on the prediction outcomes to 8 survival rate change types. The results indicate that the LSTM model can be useful in predicting and simulating the survival rate of commercial facilities. Moreover, the CBD area showed a decrease in the survival rate in the future, and the commercial districts around university districts and IT industry clusters were divided into commercial districts with an increased survival rate in the future. The results of this study are expected to be used as quantitative evidence for more direct and realistic policy establishment.
Date: 2025
References: View complete reference list from CitEc
Citations:
Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0326307 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 26307&type=printable (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0326307
DOI: 10.1371/journal.pone.0326307
Access Statistics for this article
More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().