Machine Learning Model to Forecast Demand of Boston Bike-Ride Sharing
Bibliographic record
Abstract
Bike-ride sharing systems are the new generation of traditional bike rentals, where the entire process is automated. A user rents a bike from one location and returns it at another location. There are more than 500 bike-ride sharing systems around the world, consisting of more than 500,000 bikes. Bike-ride sharing systems are typically found in urban and large cities such as Boston, N.Y. City, Washington DC, Paris, Montreal, and Barcelona. Bike-ride sharing is particularly important due to their important impact on traffic, environment, and health. As popular as bike-ride sharing systems are, there is a lack of a reliable model to forecast (predict) bike rental demand daily. Lack of available bikes constitutes an inconvenience to individuals seeking a bike at a certain location and a loss of revenues for companies operating the bikes. This paper develops a Machine Learning (ML) model (algorithm) to forecast (predict) the number of bikes rented daily based on historical data. Moreover, the model overlays environmental and seasonal settings to study their impact on bike rental demand. We test our ML model using a real-life dataset obtained from a local bike-ride sharing company in the City of Boston in the state of Massachusetts in the United States. We also applied the model to historical dataset from New York City (NYC). In both cases, the model is accurate and reliable.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".