Identifying Optimal High-Risk Driver Segments for Safety Messaging
Bibliographic record
Abstract
Given the public safety risk posed by high-risk drivers, most traffic safety agencies consider this group a key target for strategic planning purposes. The aim of this research was to develop a framework that could be used to efficiently and effectively target high-risk drivers. The specific objectives were to establish whether high-risk drivers were homogeneous and if not, to determine the optimal set of primary and secondary clusters for efficient and effective targeting with minimal resources. The study area was Saskatchewan, Canada. Multiple databases (including traffic collisions, insurance claims, and conviction data) formed the basis for the research. In this study, high-risk drivers were defined as all drivers who were enrolled both in the Driver Improvement Program of Saskatchewan Government Insurance and in the negative or penalty zone of Saskatchewan Government Insurance's safety driver rating scale as a result of accumulated demerit points. Geodemographic modeling with the neighborhood as the unit of analysis, a large number of variables, and a set of probabilistic clustering techniques were used in the analysis. The results indicated that the high-risk driver group was heterogeneous; it fell into subclusters with varying collision and traffic behavior profiles. The study found that Saskatchewan high-risk drivers were mainly in the major cities (56%) but also in rural municipalities (18%) and towns (15%). The optimal primary high-risk segments for efficient targeting were those major cities and towns where both the risk of collision involvement and the concentration of high-risk drivers were higher than the driver population. Drivers in the primary target area for messaging showed higher levels of distracted, impaired, and aggressive driving behaviors; driver inexperience; extreme fatigue; falling asleep behind the wheel; and inattention.
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) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".