Methodology
CrimeScore is a small-area statistical model. It is designed to help product teams present neighborhood context, not to make decisions about individual people.
CrimeScore produces a 0 to 100 Safety Score for Census block groups. Higher scores represent safer relative standing, and A is the best grade.
The deployed score combines violent crime, property crime, disorder, and frequency components. The API returns those component values with every successful score response.
CrimeScore works with public reported-crime records from public safety and government sources. Broad public government demographic, economic, and geographic data provides additional location context.
Race and ethnicity are excluded from model features and are not shown as score contributors. Contributor labels are descriptive model signals, not causal claims.
Standardized location signals are converted to a common scale so covered locations can be compared consistently.
Scores support local and national comparisons, but they do not predict what will happen to a person, property, or exact location.
Published results identify the model version and coverage release they use.
Reported-crime records reflect reporting and enforcement practices, not total true crime prevalence. Government estimates can lag rapid neighborhood change, and some areas have weaker source coverage.
CrimeScore should not be used for predictive policing, individual risk scoring, lending or housing discrimination, or any use prohibited by fair-housing or civil-rights law.
FAQ
No. CrimeScore is a statistical location-risk model. It does not claim that a feature causes crime.
No. Race and ethnicity are excluded from model features and are not shown as score contributors.
Coordinate requests resolve to Census block groups. ZIP code searches use Census ZCTAs, and map layers support county and state browsing.