PredPol’s Technology Helps Law Enforcement Agencies Prevent Crime

PredPol’s technology has been helping law enforcement agencies to dramatically reduce crime in jurisdictions of all types and sizes, across the U.S. and overseas.

The Crime Prediction Algorithm

The algorithm used by PredPol has been published and discussed publicly in peer-reviewed papers. It is based on the observation that certain crime types tend to cluster in time and space. PredPol uses self-exciting point process models to replicate this behavior (Click Self-Exciting Point Process Modeling of Crime).

PredPol takes a feed from each department’s Records Management System (RMS) to collect crime type, location and date/time. This data is collected at least daily and feeds our prediction engine, which is run once a day to create predictions for each beat, shift and mission type. The data collected does not include any personally identifiable information (PII).

We initially process several years of data to lay down a “background” level of crime patterns and to understand how crimes propagate throughout the city. This is done using an Epidemic Type Aftershock Sequence (ETAS) Model, which is a self-learning algorithm.

As new crimes come in, they are mapped against existing patterns and events in the city. Based on the propagation patterns uncovered by the initial analysis of the data, we predict when and where similar crimes related to these crimes are most likely to occur.

Every 6 months, we force a “re-learning” of the patterns using all historical and recent crime data. This ensures that new patterns of behavior are picked up by the system as well.

 

“We have seen anywhere from 15 to 30 percent in reduction in burglaries and robberies. I don’t care how science fiction or how far out there it is, the proof is in the pudding.” Norcross, GA Police Lt. Bill Grogan (CBS 46 Atlanta, December, 2013)

Specific to Crime Types

Using advanced mathematics and machine learning AI, PredPol’s algorithm predicts many types of street crime and other events in the following broad categories:

Property Crimes:

  • Burglary (residential and commercial)
  • Auto theft
  • Vehicle break-ins
  • Other grand larcenies

Personal Crimes:

  • Robbery
  • Aggravated assault
  • Gang activity
  • Gun violence

Traffic Incidents:

  • Collisions
  • DUIs

“We can look at overall crime, or we can go to a particular zone…simply, the type of crime, the time of day the incident happened, and the location. They run it through their mathematical algorithm, and the end result is boxes.” Atlanta, GA Police Department Lt. LeAnn Browning (WSB-TV 2 Atlanta, September, 2013)

Command Analytics

PredPol goes beyond predictive policing with Command Analytics. Command Analytics is a suite of high-level features designed for command staff, watch/shift supervisors, detectives and crime analysts. Command Analytics is designed to provide quick and simple access to data from records management systems (RMSs), GPS tracking systems, and other departmental data stores.

Our suite offers real time analysis tools for decision making, resource management, and planning through the following features:

  • Crime search
  • Mission Control
  • Radar
  • GPS + Vehicle Pathing.

Secure & Reliable Access

  • PredPol is hosted on a secure, cloud-based software-as-a-service (SaaS) platform.
  • Personal information about victims, offenders, or law enforcement is NOT collected or stored, ever.
  • All of PredPol’s data processing facilities employ keycard protocols, biometric scanning, and round-the-clock interior and exterior surveillance.

 

“The theory is that you prevent them from committing the crime to begin with…Burglars and thieves work in a mathematical way, whether they know it or not.” Modesto Police Chief Galen Carroll (Modesto Bee, July 27, 2014)

 

Quantcast