Optimize a chain convenience store location prediction model by using MTS-machine learning methodology
Tsung-Yin Ou, Hsin-Pin Fu, Mei-Zhen Wu · 2025
Read Optimize a chain convenience store location prediction model by using MTS-machine learning methodology by Tsung-Yin Ou, Hsin-Pin Fu, Mei-Zhen Wu (2025) 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/pmc-12783830.txt.
Description
Tsung-Yin Ou, Hsin-Pin Fu, and Mei-Zhen Wu built a store site prediction model in 2025. Picking convenience store sites once took long field research. Choices leaned heavily on a manager's gut feel. Machine learning now offers a data-driven route. Their hybrid method first trims the variable list. A statistical system cut nine candidate factors to five. Three learning algorithms then trained on Taiwan store data. They were a boosting method, a forest method, and a support vector method.
The trimmed boosting model held accuracy above three quarters. That held across varied training data shares. It beat the forest and support vector versions clearly. Fewer variables cut computing needs. The authors say chains can decide sites faster this way. Decisions rest on data rather than habit. They present the model as a planning tool for retail strategy. Multi-factor site problems suit it best, they argue.
Catalog record
| CREATOR | Tsung-Yin Ou, Hsin-Pin Fu, Mei-Zhen Wu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |