Prediction of Fatalities in Vehicle Collisions in Canada
Bibliographic record
Abstract
Traffic collisions affect millions around the world and are the leading cause of death for children and young adults. Thus, Canada’s road safety plan is to reduce collision injuries and fatalities with a vision of making the safest roads in the world. We aim to predict fatalities of collisions on Canadian roads, and to discover causation of fatalities through exploratory data analysis and machine learning techniques. We analyse the vehicle collisions from Canada’s National Collision Database (1999–2017.) Through data mining methodologies, we investigate association rules and key contributing factors that lead to fatalities. Then, we propose two supervised learning classification models, Lasso Regression and XGBoost, to predict fatalities. Our analysis shows the deadliness of head-on collisions, especially in non-intersection areas with lacking traffic control systems. We also reveal that most collision fatalities occur in non-extreme weather and road conditions. Our prediction models show that the best classifier of fatalities is XGBoost with 83% accuracy. Its most important features are “collision configuration” and “used safety devices” elements, outnumbering attributes such as vehicle year, collision time, age, or sex of the individual. Our exploratory and predictive analysis reveal the importance of road design and traffic safety education.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".