Data-Driven Patrol Management to Meet Today’s Challenges
Patrol Management Software for Better Resource Deployment Decision-Making
ShotSpotter’s patrol management software uses artificial intelligence-driven analysis to help strategically plan directed patrols that feature consistent tactics designed to maximize crime deterrence with minimal harm to the community.
Directed Patrols Prevent Crime
Research shows that high visibility patrols are an effective deterrent to crime. Agencies receive precise locations to patrol based on AI that is superior to traditional hot spot analysis.
- Boxes represent a precise area (250 meters by 250 meters) for patrol and are color coded by crime type.
- When officers arrive into a box, the directed patrol officially begins and a timer starts so that the area is not over or under patrolled.
- Authorized users such as crime analysts can add or suppress a directed patrol based on late-breaking information.
- The directed patrols can be viewed on an MDT, smartphone, desktop, or printed out.
- ShotSpotter Connect uses historical and continuously updated ShotSpotter gunfire data to create enhanced gunfire forecasts since the community typically reports only 20% of gunfire.
Suggested Tactics for Optimal Outcomes
Data-driven patrol plans put your officers in the right place at the right time while a list of low-touch interventions promote community trust
- As officers enter a directed patrol area, they are presented with approved non-enforcement oriented tactics to use during the patrol.
- The system tracks officer time spent in directed patrol areas and tactics used.
- Tactics are configurable and agencies are encouraged to review their tactics with the community.
Community First: Mitigating Bias and Over-Policing
ShotSpotter’s unique Community First approach has three protections in place to help establish impartiality when determining where patrols are conducted. First, the system intelligently meters out where patrol assignments occur and limits their duration to reduce instances of over-policing. Second, the system ensures the algorithms that drive patrol recommendations use objective, non-crime data that mitigates potential bias. Third, the system does not use any personally identifiable information to determine where patrols should be assigned.
Use Objective, Non-Crime Data
No Personally Identifiable Info
How ShotSpotter Connect Works
How can ShotSpotter® Connect™ benefit a police department and community?
- Detects areas at highest risk for crime on a shift-by-shift and beat-by-beat basis
- Protects the community by helping law enforcement know the right place and time to patrol to deter crime and in a way that minimizes bias and over-policing
- Connects officer tactics and dosage to their crime impact so police can better measure and optimize their patrol strategies
What crime types does it forecast?
- Part 1 Crimes: Gunfire, homicide, aggravated assault/battery, robbery, burglary, motor vehicle theft, and theft
- A few Part 2 crimes such as simple assault and destruction/damage/vandalism
Can it track only crime types that are of interest to an agency?
- Yes, crime forecasts can be configured based on those crimes of interest to a police department. For larger agencies, each district or special enforcement unit may have their own crime type priorities and that can be easily accommodated.
- A separate risk model is created for each crime type enabling the technology to have a unique configuration for each agency and their jurisdictions that use it
- However Connect will not model crimes that are largely susceptible to enforcement bias
What data feeds into the crime risk models?
- Connect uses historical ShotSpotter detected gunfire incidents, historical crime incidents, seasonality, time of day, day of week, census data, upcoming events, and environmental features (e.g., density of bars, density of vacant parcels, etc.).
- ShotSpotter Connect does not include any race or educational data
- ShotSpotter Connect does not use any personally identifiable information about specific residents, such as whether a neighborhood has a certain number of parolees or sex offenders or its demographics. It is focused on creating risk assessments for where and when crimes will occur, not who will commit them.
What kind of protections does Connect have to minimize bias or discrimination?
- We use crime data that is least susceptible to bias – Our models only use data for crime types that are typically called in from the community and not driven by police presence. We exclude misdemeanor and nuisance crimes that can create negative feedback loops with enforcement bias. These loops can occur in other modeling approaches when police presence in an area can repeatedly return police to the same area.
- We supplement crime data modeling with non-crime data and exclude people data – We also work to reduce bias by supplementing reported data with multiple sources of relevant data from independent, open sources. Typical examples include seasonality, time of month, day of week, time of day, holidays, upcoming events, weather, and locations of liquor establishments.
- We maximize the reduction of harm – We do not make predictions about the actions of people – that means no arrests, social media, or personal data is used. We limit the time an officer patrols and the occurrence of patrol assignments in the same location to prevent over-patrolling
- We prioritize oversight and accountability – We log data input used and outputs generated by each model. We also log patrol activities including time, place and tactics used.
- We are proactively transparent – We are committed to being transparent about how our system works and use third parties to provide objective assessments. We proactively, self-volunteered for an audit by New York Law School’s Policing Project, which is in progress. We are adopting their recommendations to strengthen and enhance transparency and community protections.