Utilització de tècniques de data science per a la modelització de la demanda dels serveis de bicicletes en autoservei Bixi de Montreal
Bibliographic record
Abstract
The final master thesis investigate behavioural patterns of the users of bike-sharing system BIXI in Montreal. A data mining approach is used by applying clustering methods on open data from BIXI, the Government of Canada and the City of Montreal. Hierarchical clustering with Ward and Gower is processed to form clusters using only the BIXI variables at first. Then, because the authors believe that contextual information has a fundamental effect on the user’s behaviour, they investigate the impact of adding such information into the clustering methodology. In the end, a multi-view clustering method is preferred for its quality of preserving the basic characteristics of simpler set of clusters (mixing less variables). Afterwards, local analysis are done over some profiles of the classes. A dynamic balancing analysis of the station using geographical representation offer good insight on the movements of the bikes associated with a cluster. Then, a complex network approach is also used to extract more topological information about the bike-sharing network made from the stations and the trips. All these transdisciplinary approaches used together produce new operational knowledge that can be useful for the operators and the logistics to overcome the redistribution problem as well as improving the quality of the service.
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 | 0.013 | 0.037 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.007 | 0.003 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.004 |
| Insufficient payload (model declined to judge) | 0.004 | 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".