How Predictive Policing Works

Predictive Policing: Guidance on Where and When to Patrol

PredPol uses a machine-learning algorithm to calculate its predictions. Historical event datasets are used to train the algorithm for each new city (ideally 2 to 5 years of data). It then updates the algorithm each day with new events as they are received from the department. This information comes from the agency’s records management system (RMS).

PredPol uses ONLY 3 data points – crime type, crime location, and crime date/time – to create its predictions. No personally identifiable information is ever used. No demographic, ethnic or socio-economic information is ever used. This eliminates the possibility for privacy or civil rights violations seen with other intelligence-led policing models.

Predictions are displayed as red boxes on a web interface via Google Maps. Each box is a 150×150-meter square. The boxes represent the highest-risk areas for each day and for the corresponding shift: day, swing or night shift. Officers are instructed to spend roughly 10% their shift time patrolling PredPol boxes.

Download our white paper on the Science & Testing of Predictive Policing

Patrol Operations: Mission Planning and Location Management

PredPol lets you set specific missions for each shift, beat and day of the week. Missions are collections of selected crimes or events. PredPol displays the highest-probability locations for the events associated with each mission.

If your agency has GPS or AVL, PredPol can also track “dosage” of PredPol boxes. Dosage refers to the amount of time officers spend in PredPol boxes. This allows command staff to ensure that recommended areas are being patrolled.

PredPol also creates patrol heat maps that allow command staff to see if any areas of their jurisdiction are being under patrolled.

Chief Mark Yokoyama“PredPol does not replace the experience and intuition of our great officers, but is rather an invaluable added tool that allows our police force to use their patrol time more efficiently and helps stop crime before it happens.” Chief Mark Yokoyama (SVG Journal)

Analytics: Closing the Loop with Data and Reporting

We believe that your data belongs to you and you should be able to access it quickly and painlessly. PredPol allows you to see your crime and operations data graphically as well as download it in CSV or PDF format.

PredPol’s analytics and reporting module provides a quick summary of a rich and complex dataset. Our point-and-click interface lets you create custom reports instantly – by any combination of crime types, missions, districts and shifts over any date range. The goal is to simplify the underlying data and present it in an actionable format. It is used for activities such as mission planning and setting resource levels. This follows the philosophy “you can’t manage what you don’t measure.”

This information can also be shared with local government or the community to see the relative patrol coverage across the city. It is a key element of the transparency that PredPol is trying to bring to police departments and the communities they serve.

Download our white paper on Predictive Security for the Private Sector

Captain Sean Malinowski“We told [officers] to go into the boxes and use their knowledge, skills and experience to determine what should be done…They may stay there for just 15 minutes to a half-hour and let people see them walking around the area…Would-be offenders see the police activity and are deterred from committing a crime there. All we are trying to do is deny them the opportunity to commit that crime in that time and place. During our test, we probably disrupted criminal activity eight to 10 times a week….” LAPD Foothill Division Captain Sean Malinowski (Officer.com, January 1, 2013)