Analysis and Prediction of Bike-Sharing Demand in Bergen Using Machine Learning and Weather Data
This research paper investigates the key factors influencing bike-sharing demand in Bergen, Norway. By analyzing comprehensive trip data alongside meteorological variables (temperature, wind speed, precipitation, humidity, and sunshine) and calendar indicators (season, holidays, and weekends), the study identifies the primary drivers of ridership patterns.The findings align with existing literature, confirming that adverse weather conditions significantly reduce bike-sharing usage, while temporal factors such as the time of day, day of the week, and season play a critical role in demand fluctuations. By quantifying the impact of these environmental and temporal variables, this study provides actionable insights for urban planners and bike-sharing operators. These insights can be used to optimize fleet distribution, improve station management, and enhance overall service reliability in varying weather conditions, ultimately supporting more sustainable urban mobility.
Authors
- Sareena Bilal
Publication Details
- Journal
- Figshare
- Published
- 2026-11-15
- DOI
- https://doi.org/10.6084/m9.figshare.35013865
- Primary Topic
- Urban Transport and Accessibility
- Type
- preprint