Predictive Analytics of Streetcar Bunching Occurrence Time for Real-Time Applications
Bibliographic record
Abstract
Bunching occurs when transit vehicles are unable to maintain their scheduled headways, resulting in two or more vehicles arriving at a stop in close succession and following each other too closely thereafter. Very few studies have explored the prediction of bunching in real-time, particularly for streetcar services. Predicting the time to bunching in real-time allows transit agencies to take more preventive actions to avoid the occurrence of bunching or to minimize its effects. In this study, we present a comprehensive literature review of the recent research conducted in bunching and real-time prediction models. Based on the findings from the literature review, we propose a model for real-time prediction of streetcar bunching. The Kalman filtering model predicts the travel time to bunching incidents and is tested and analyzed using an automatic vehicle location data feed for one streetcar route (Route 506 Carlton), obtained from the Toronto Transit Commission’s next bus system. The results show that: (1) the model provides good predication quality given that it relies only on the real-time GPS feed of streetcars, which makes it practical for use in real-time prediction applications; (2) the model prediction accuracy improves as the transit vehicle travels away from the terminal; and (3) increasing the number of past days involved in the calculations beyond 6 days or increasing the number of leading trips considered in the same day beyond 7 or 10 trips might increase the prediction error.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| 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) | 0.001 | 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 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".