Leveraging System Intelligence from Massive Smart Card Database to Support Operational and Strategic Objectives of a Transit Agency
Bibliographic record
Abstract
Transit agencies have long been operating in data-poor environments. They have been relying on labour-intensive and project-specific data collection, which are often sparse and costly. Recently, the adoption of technologies that generate passive data streams has become increasingly common. One of such technologies is the smart card automatic fare collection (AFC) system which provides a massive database containing detailed and up-to-date fare validation records. An important preoccupation of both practitioners and researchers is to transform the raw and often partial data into useful information. Various aspects of a transit agency, from day-to-day operations to strategic rethinking of the transit system, can benefit from such intelligence. While data timeliness of smart card data is an obvious advantage over other data collection methods, data organization and processing are important issues. Each application, aiming to tackle a specific problem, requires a different approach and data enrichment procedure. Drawing data and experience from the Montreal region, which currently operates an extensive multi-region, multimodal and multi-operator smart card AFC system that generates two million transactions per day, this paper presents contributions of smart card intelligence within a regional transit authority context by showcasing several real-world applications on transit services, transit equipment and fare use. Smart card data analytics provide different departments within the organization and among partner organizations in the region access to up-to-date and previously unavailable information. This in turn allows them to make more informed decision on policies and plans. The future of public transit relies greatly on adequate data and intelligence. The next steps would be to expand the number of applications, to put in place a structure that facilitates systematic and corporate use of the data and to increase cooperation among partner organizations.
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 | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.006 | 0.007 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".