Optimizing bike-sharing station locations: A machine learning and artificial neural networks approach using geospatial and demographic data
Marek Weis, Wojciech Dawid · 2026
Read Optimizing bike-sharing station locations: A machine learning and artificial neural networks approach using geospatial and demographic data by Marek Weis, Wojciech Dawid (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-0349339.txt.
Description
Marek Weis and Wojciech Dawid trained a machine learning model to pick good locations for bike-sharing stations, a planning problem with many tangled factors. The model learned from land cover and population data around existing successful stations, comparing several learning methods including neural networks. It reached very high accuracy in identifying suitable spots.
Predicted stations matched the real network's logic and suggested sensible expansion points, clustered near big intersections and transit stops. As a harder test, the model was turned loose on Rzeszów, a Polish city with no bike system yet, and proposed a coherent starter network. Cities weighing a launch could use such a model to argue site choices with evidence instead of hunches.
Catalog record
| CREATOR | Marek Weis, Wojciech Dawid |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54197 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |