Development of Macro-Level Crime and Collision Prediction Models to Support Data-Driven Approach to Crime and Traffic Safety (DDACTS)
Bibliographic record
Abstract
The number of violent crimes and fatal-injury collisions concerns many jurisdictions. Traditional enforcement tactics are often reactive, relying on historical crime and collision data to select locations for law enforcement. Advanced law enforcement tactics take a proactive approach. Such tactics include Data-Driven Approaches to Crime and Traffic Safety (DDACTS), which uses predicted numbers of crimes and collisions to identify locations for law enforcement. This DDACTS study was conducted in Regina, Saskatchewan, Canada. The research developed macro-level prediction models to predict violent crimes and collisions in each traffic analysis zone (TAZ) in Regina. The zonal nature of the analysis is important for overcoming confidentiality and privacy issues associated with violent crimes and fatal-injury collisions. Fifty-four input variables were used to describe each TAZ’s crimes, collisions, socio-demographic, road inventory, traffic, and land use characteristics. The analysis used negative binomial regression coupled with the empirical Bayes method (a popular approach in transportation, but relatively new to crime mapping) to develop two statistical models that predict the long-term mean value for the number of violent crimes/collisions per zone. Cumulative residual plots were used as the main goodness-of-fit test. The findings are summarized on a map showing the top ten hotzones for violent crimes, the top ten hotzones for fatal-injury collisions, and the zones where the crime and collisions zones overlap. The overlapping zones are the DDACTS zones. By focusing law enforcement in the DDACTS zones, it may be possible to reduce violent crimes and fatal-injury collisions simultaneously and use limited resources more cost effectively.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| 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".