Designing an Explainable Predictive Policing Model to Forecast Police Workforce Distribution in Cities
Bibliographic record
Abstract
Despite extensive research, measurable benefits of predictive policing are scarce. We argue that powerful models might not always help the work of officers. Furthermore, developed models are often unexplainable, leading to trust issues between police intuition and machine-made prediction. We use a joint approach, mixing criminology and data science knowledge, to design an explainable predictive policing model. The proposed model (a set of explainable decision trees) can predict police resource requirement across the city and explain this prediction based on human-understandable cues (i.e., past event information, weather, and socio-demographic information). The explainable decision tree is then compared to a non-explainable model (i.e., a neural network) to compare performance. Analyzing the decision tree behaviour revealed multiple relations with established criminology knowledge. Weather and recent event distribution were found to be the most useful predictors of police workforce resource. Despite wide research showing relationships between socio-demographic information and police activity, socio-demographic information did not contribute much to the model’s performance. Though there is a lack of research on measurable effects of predictive policing applications, we argue that combining human instinct with machine prediction reduces risks of human knowledge loss, machine bias, and lack of confidence in the system.
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) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 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 | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".