This is like drawing a big map of who knows who in a city, then using math to see which people or groups are at the centre of crime activity or at highest risk of becoming victims. Instead of only looking at individual incidents, it looks at the web of relationships around them.
Traditional crime analysis focuses on incidents, locations, and individuals in isolation. This approach uses social network analysis to identify high‑risk groups, key influencers, and hidden structures (e.g., gangs, co‑offending networks, victimisation clusters), enabling more targeted policing, prevention, and victim support.
Access to detailed law-enforcement, court, and social-service data, plus longitudinal network data on offenders and victims, which are hard for others to replicate and can become a proprietary analytical asset for the public agency or research institution.
Classical-ML (Scikit/XGBoost)
Structured SQL
Medium (Integration logic)
Complexity and privacy constraints when building and maintaining large, dynamic social graphs from sensitive criminal justice and victimisation data.
Early Majority
Focuses specifically on applying social network analysis to crime and victimisation rather than generic network analytics, aligning methodology with public safety, criminology, and victim support use cases in the public sector.