Mining Smart Card Data from an Urban Transit Network
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
In large urban areas, smooth running public transit networks are key to viable development. Currently, economic and environmental issues are fueling the need for these networks to adequately serve travel demand, thereby increasing their competitiveness and their market share. Better balance between transit supply and demand will also help reduce and control operating costs. The fact is, however, that transit operators are finding it extremely difficult to adjust the service to meet the demand, because this demand changes continuously with the time or day of travel (period of the day, day of the week, season or holiday) and other factors like weather and service breakdown. In order to enhance their service, operators need to better understand the travel demand (customer behaviors and the variability of the demand in space and time). This can be achieved only by continuously monitoring the day-to-day activities of users throughout the transit network. Some large cities around the world take advantage of smart card capabilities to manage their transit networks by using Smart Card Automated Fare Collection Systems (SCAFCS). An SCAFCS gives travelers greater flexibility, since a single card may be used by one user at various times and on different parts of the transit network, and may support various fare possibilities (by travel, line, zone, period, etc.). For transit operators, these systems not only validate and collect fares, but also represent a rich source of continuous data regarding the use of their network. Actually, this continuous dataset (developed for fare collection) has the potential to provide new knowledge about transit use. Following the application of various pretreatments which make it possible to extract real-time activity, data mining techniques can reveal interesting patterns. These techniques are aimed at precisely describing customer behavior, identifying sets of customers with similar behaviors, and measuring the spatial and temporal variability of transit use. Patterns are extracted and analyzed to document various issues, such as identifying transit use cycles or homogeneous days and weeks of travel for various periods of the year. This information is required for a better understanding and modeling of customer behavior, and consequently better adjustment of the service to the demand. These adjustments may, for instance, lead to the restructuring of the transit network, to the adaptation of route scheduling or to the definition of new and different subscription options (fares). Below, results from various experiments conducted with a real dataset are provided. They show the potential of data mining to provide useful and novel information about user behavior on a transit network. The data processed in the study are extracted from a system operating in a Canadian city (Gatineau, Quebec).
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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