A Study on the Application of Data Mining-based Crime Prediction Models in Criminal Justice
Bibliographic record
Abstract
With the social progress and technological development, China’s criminal activities gradually show the characteristics of specialization, networking, and hotspotting, which leads to the phenomenon of high incidence but low detection rate, and the prediction of the criminal phenomenon is particularly important. In this paper, we construct a graph self-encoder, and derive the formula of the GAE loss function from the corresponding reconstructed neighbor matrix and node feature loss function of GAE. The spatial channel attention mechanism is introduced to improve the performance of the model, and the time window dimension is mapped to the perceptual self-attention module, and the objective function is constructed by generating a collection of crime matrices for future time windows. A multi-raster layer analysis model is added to optimize the model, generate a risk map of criminal activities, quantify the risk value of each element, and form a spatio-temporal prediction effect. Comparison experiments are used to analyze the optimization effect of the model, and the absolute error of the optimized model is no more than 0.05 for four types of cases. The prediction results of the cases of property invasion in different time periods show that the number of cases occurring in the early hours of the morning is 508, and the average PEI index is 0.19, which is smaller compared with other time periods.
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 | 0.003 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| 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".