Uncovering traditional retail location competition with machine learning: The role of urban environments in light-asset and capital-intensive formats
Yueyi Tan, Jusheng Song, Guangying Zhao, Yunxi Bai, Yan Li, Xuren Wei · 2026
Read Uncovering traditional retail location competition with machine learning: The role of urban environments in light-asset and capital-intensive formats by Yueyi Tan, Jusheng Song, Guangying Zhao, Yunxi Bai, Yan Li, Xuren Wei (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0358597.txt.
Description
Yueyi Tan leads a team of six using machine learning to map how two kinds of shops compete for space in Shenzhen, China, in PLOS ONE in 2026. Convenience stores run light, cheap, and everywhere; supermarkets and malls are capital heavy and choosy. The team fed geospatial data and measures of how people perceive streets into a stack of interpretive models that can reveal bends and interactions, not just straight line effects.
The two formats followed distinct locational logics. Convenience stores spread widely and reacted strongly to nearby competition, to the proximity of everyday services, and to how a place feels to pedestrians. The big formats clustered where returns justify their cost. Untangling which urban features pull each format helps planners zone commercial districts deliberately, and helps chains pick sites with their eyes open about which game they are playing.
Catalog record
| CREATOR | Yueyi Tan, Jusheng Song, Guangying Zhao, Yunxi Bai, Yan Li, Xuren Wei |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 94095 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |