White Collar Crime Risk Zones
summary
A predictive-policing style system uses parsed FINRA PDF enforcement records plus features like nonprofit, liquor store and investment-adviser densities to train risk terrain modeling and produces a New York City block map of white-collar crime risk; the demo claims 90.12% accuracy, colors squares by predicted risk and lists likely crime types, severity and nearby institutional suspects, and it generates a facial average from LinkedIn profiles for a composite “most likely” offender.
AI-written summary · about
related talks
20mFighting Corruption with Technology
23mUsing AI to Prevent Residential Burglary in Berlin
45mBias in Artificial Intelligence
33mAssurance Scoring Using Machine Learning and Analytics to Reduce Risk in the Public Sector
52mModern Fraud Prevention Using Deep Learning
34mWhen Prediction Becomes Policy: What Do Risk Models Actually Learn?
26mSridhar Telidevara: Professor, Great Lakes Institute of Management at Cypher 2017 - Part 1/2
07mMapping Urban Deprivation