Station-Level Forecasting of Bikesharing Ridership
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This study investigated the effects on bikesharing ridership levels of demographic and built environment characteristics near bikesharing stations in three operational U.S. systems. Although earlier studies focused on the analysis of a single system, the increasing availability of station-level ridership data has created the opportunity to compare experiences across systems. In this study, particular attention was paid to data quality and consistency issues raised by a multicity analysis. This project also expanded on earlier studies with the inclusion of the network effects of the size and spatial distribution of the bikesharing station network, which contributed to a more robust regression model for the prediction of station ridership. The regression analysis identified a number of variables that had statistically significant correlations with station-level bikesharing ridership: population density; retail job density; bike, walk, and transit commuters; median income; education; presence of bikeways; nonwhite population (negative association); days of precipitation (negative association); and proximity to a network of other bikesharing stations. Proximity to a greater number of other bike-sharing stations exhibited a strong positive correlation with ridership in a variety of model specifications. This finding suggested that, with the other demographic and built environment variables controlled for, access to a comprehensive network of stations was a critical factor to support ridership. Compared with earlier models, this model is more widely applicable to a diverse range of communities and can help those interested in the adoption of bikesharing systems to predict potential levels of ridership and to identify station locations that serve the greatest number of riders.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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 it