AI-powered safety prediction and risk assessment APIs for location-based threat analysis.
Added statistical baseline model providing daily/hourly granularity and detailed crime type breakdowns
Daily Predictions: Get expected crime counts for any specific day, not just weekly aggregates
Hourly Breakdowns: Understand when crime is most likely throughout the day with peak hour analysis
Detailed Crime Types: See breakdown within categories (e.g., within "Theft", what percentage is vehicle break-ins vs shoplifting)
Confidence Intervals: Statistical bounds on predictions (e.g., "expect 12 crimes, 95% confidence between 8-17")
The API now provides insights from two models in a single response:
| Model | Strengths |
|---|---|
| Primary (Deep Learning) | Weekly patterns, spatial relationships, probability distributions |
| Baseline (Statistical) | Daily/hourly precision, specific crime types, confidence intervals |
Predictions now include:
All 10 cities now have baseline models that train in under 60 seconds, enabling rapid updates as new data becomes available.
Predictions now include expected crime counts alongside probability distributions
Expected Crime Counts: The model now predicts not just "what type of crime" but also "how many crimes" to expect in each area
Per-Type Volume Breakdown: Get expected counts broken down by crime category (e.g., "expect 3 thefts, 2 assaults this week")
Before: "This area has 35% theft probability, 25% assault" After: "This area has 35% theft (expect ~3 incidents), 25% assault (expect ~2 incidents), 8.5 total crimes expected"
Every city model has been retrained with dual prediction capabilities:
| City | Distribution Error | Count Correlation |
|---|---|---|
| London | 3.54% | 0.62 |
| Chicago | 3.99% | 0.88 |
| NYC | 4.33% | 0.77 |
| LA | 4.44% | 0.80 |
| Philadelphia | 4.69% | 0.87 |
| SF | 4.79% | 0.79 |
| Denver | 4.82% | 0.62 |
| Toronto | 4.82% | 0.79 |
| Boston | 5.82% | 0.85 |
| Seattle | 6.19% | 0.86 |
All prediction endpoints now include:
expected_total: Total crimes expected in the time periodexpected_counts: Breakdown by crime typecount_mae: Model accuracy for volume predictionsAdded Boston, Toronto, and Denver to reach full 10-city milestone
Three new cities complete our initial 10-city goal:
The platform now covers 3 countries:
| Rank | City | Prediction Error |
|---|---|---|
| 1 | NYC | 3.73% |
| 2 | Chicago | 3.82% |
| 3 | London | 4.02% |
| 4 | Philadelphia | 4.85% |
| 5 | Denver | 4.92% |
| 6 | LA | 5.23% |
| 7 | Toronto | 5.90% |
| 8 | SF | 6.26% |
| 9 | Seattle | 6.65% |
| 10 | Boston | 7.85% |
Added San Francisco, Los Angeles, Seattle, and Philadelphia in a single day
Four new US cities added to the prediction platform:
| City | Grid Cells | Prediction Error |
|---|---|---|
| NYC | 446 | 3.73% |
| Chicago | 278 | 3.82% |
| London | 590 | 4.02% |
| Philadelphia | 163 | 4.85% |
| LA | 585 | 5.23% |
| SF | 30 | 6.26% |
| Seattle | 93 | 6.65% |
Added comprehensive crime predictions for all five NYC boroughs
New York City Coverage: Full crime prediction support across Manhattan, Brooklyn, Queens, The Bronx, and Staten Island
Best-Performing Model: NYC achieves our lowest prediction error yet at 3.73%, thanks to extensive historical data
| City | Grid Cells | Prediction Error | Records |
|---|---|---|---|
| NYC | 446 | 3.73% | 1.5M |
| Chicago | 278 | 3.82% | 1.2M |
| London | 590 | 4.02% | 800K |
The unified endpoint now serves predictions for three major cities across two continents. Existing integrations continue to work unchanged - just send coordinates and receive predictions.
Crime predictions now available for London, UK alongside Chicago with unified auto-routing API
London Coverage: Full crime prediction support for Greater London using Metropolitan Police data
Unified API with Auto-Routing: Send coordinates from any supported city - the API automatically detects location and routes to the correct model
International Expansion: First cross-Atlantic deployment, proving the system works with different police data formats and crime categorizations
| City | Grid Cells | Prediction Accuracy |
|---|---|---|
| Chicago | 278 | 4.32% error |
| London | 590 | 4.02% error |
No changes needed to your integration. Simply send coordinates:
Adopted industry-standard hexagonal grid system for consistent worldwide coverage
Hexagonal Grid System: Migrated from custom square grids to the industry-standard H3 hexagonal system used by major rideshare and logistics companies
Globally Unique Cell IDs: Every prediction cell now has a unique identifier that works anywhere on Earth, enabling multi-city expansion
Unlike squares where corners are 40% farther from the center than edges, hexagons have uniform neighbor distances. This creates more consistent spatial patterns for the model to learn, resulting in better predictions.
First public release of the crime prediction API with single location, batch, and route risk endpoints
Single Location Predictions: Send any latitude/longitude in Chicago and receive a complete crime probability distribution with risk level assessment
Batch Predictions: Query up to 100 locations in a single request with summary statistics across all locations
Route Risk Assessment: Calculate cumulative crime risk along a travel route with segment-by-segment breakdown and customizable risk weighting
| Endpoint | Description |
|---|---|
| Single Prediction | Get crime probabilities for any location |
| Batch Prediction | Compare multiple locations at once |
| Route Risk | Assess safety along a planned route |
| Coverage Info | Check available geographic bounds |
For each prediction request, you receive:
Redesigned crime categories and optimized model weights to achieve industry-leading accuracy
Redesigned Crime Categories: Restructured crime classifications into more balanced and meaningful groups for better predictions
Probability Distribution Focus: Shifted focus from simple classification to full probability distributions - now providing the complete picture of crime likelihood
Previously, the system would tell you "this area is high risk for property crime." Now it tells you the complete breakdown: "35% theft risk, 25% assault risk, 20% quiet, 15% vehicle damage, 5% other." This full distribution enables better decision-making.
Enhanced crime prediction model with better probability calibration and honest geographic boundaries
More Accurate Probability Predictions: The model now outputs well-calibrated probability distributions, meaning when we say "35% chance of property crime," you can trust that number
Smarter Handling of Low-Activity Areas: Added intelligent classification for areas with minimal crime activity, preventing false positives in quiet neighborhoods
Honest Geographic Boundaries: Refined the prediction coverage to focus only on populated areas, ensuring accuracy metrics reflect real-world performance