ShotSpotter Connect
Frequently Asked Questions

Connect does not model misdemeanor or nuisance crimes that are more susceptible to enforcement bias. Specifically, it models the major crimes that have an outsized impact on the community:

• Part 1 Crimes: Gunfire, homicide, aggravated assault/battery, robbery, burglary, motor vehicle theft, and theft.
• Connect will not model crimes that are largely susceptible to enforcement bias.

• 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.

• 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.

ShotSpotter seeks to reduce crime with its solutions, but that capability alone is not enough to make a public safety solution of benefit to a community. The product must provide more benefit than harm. The company has incorporated technology and policy protections to mitigate bias and discrimination yet still yield a significant public safety benefit. These protections include:

• 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.

When evaluating Connect, one must consider what method is currently being used by the agency to determine where and when they patrol to maximize crime prevention. The approaches available have good intention but can do more harm than good. Some agencies use “predictive policing” or hot spot analysis. These solutions typically use biased crime data that can create negative feedback loops and bias toward micro-communities and have no limiters on patrol time and frequency, an little tracking for account and impact analysis. Other agencies use “gut-based” plans where uncommitted time patrolling is left entirely to the discretion of the patrol officers and their subjective judgments. ShotSpotter Connect intelligently meters out where direct patrols should occur, provides recommendations on low touch, non-enforcement interventions such as simply driving through an area, parking, foot patrol and visiting a business owner. It also limits the frequency and duration of the patrols to reduce instances of over-policing

The forecasts are generally updated for each shift, but this is configurable and can be updated more often.

Officers know their beats well and may be skeptical of an analytical tool that can provide further benefits. The product supplements officer knowledge and hunches with data that is constantly being collected and analyzed. It enables officers to hit the streets with the added intelligence to be on the lookout for and prepare them for what they might face.

A robust suite of reports provides command staff with insights into where officers were and what they were doing that help optimize patrol strategies and ensure officer accountability:

• The Shift Report shows where officers were and what they were doing over time
• The Tactic Report measures and evaluates what tactics officers are using to deter crime
• The Officer Report shows time spent on each tactic
• The Crime Type Report shows time spent on directed patrols by officer for each crime type.

• The system automates routine labor-intensive data input and analytical tasks that crime analysts would typically spend hours on. This creates time for higher value-added activities like assisting with investigations and developing effective strategies to address crime.
• Analysts or other authorized users can add or suppress directed patrols based on new events or intelligence or swings in patrol capacity
• The robust reporting suite enables crime analysts and agency leadership to make more informed resource deployment decisions and improve officer accountability to more effectively drive crime deterrence.

The product proactively recommends low-touch, non-enforcement tactics to officers once they arrive at the directed patrol area such as foot patrol, talking to business owners, knocking on doors, etc. These tactics are based on the crime type, other agency best practices and the local agency’s preferences. The system also tracks the tactics so they can be analyzed and correlated to the impact on crime and help optimize operational practices.

• Crime Prevention: Precise directed patrols based on AI that simultaneously use multiple crime theories are superior to traditional hot spot analysis and maximize crime deterrence. Includes exclusive integration with ShotSpotter gunfire detection data.
• Force Multiplier: In an era of increasingly limited resources, agencies can use fewer officers directed to the right places at the right times while getting a bigger impact.
• Limit Over-Policing and Potential Bias: The exclusive feedback loop limiter helps reduce the instances of over-policing in areas that approach saturation, showing respect for the community.
• Visibility into Patrol Activities: A suite of reports provides command staff with insights into where officers were and what they were doing to help optimize patrol strategies and ensure officer accountability.
• Flexibility: The system is highly flexible and can be configured to an agency’s needs such as choosing which crime types to focus on, weighting those crime types relative to each other, and specifying which tactics to use and track.
• Support: ShotSpotter has the resources and commitment to ensure your use of Connect is a success for your department and community. We have a team of data scientists, engineers, customer success and support team members to ensure your satisfaction.

• It is a relatively straightforward and streamlined deployment process. Step one is getting data integration feeds from police RMS with historical crime data. There is an option to include vehicle location data via AVL to track officer engagement.
• Step two is ShotSpotter setting up the system using the police mapping and beat data and configuring the system to an agency’s needs
• Step three is having ShotSpotter load and set up the logic for patrol tactics and activities
• The deployment process can be completed in 60-90 days with onboarding of officers and go live following soon thereafter

• There is a tiered annual subscription fee based on the size of the agency that includes 24x7x365 customer support and best practices consulting assistance
• There is also a one-time set up fee that includes provisioning the account; agency data integrations; configuration of maps, crimes types, and tactics; model creation; and training and best practices