ShotSpotter got police to gunfire sooner, but crime did not fall

In an NIJ-funded evaluation, Kansas City officers reached ShotSpotter alerts in 266.82 s against 390.87 s for citizen calls, and NIBIN evidence collection rose 30.4%. Crime did not fall.

  • 2 for an organization

    Kansas City officers reached shots-fired alerts about two minutes sooner than citizen calls and stopped closer to the gunfire, and NIBIN evidence collection was 30.4% higher in the covered area.

  • Not rated society

    Shootings and case clearance did not improve in either city, so no gain for residents is established.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Partly reported benefit.
Evidence

foundstudiedreportedclaimed

An independent evaluation report supports the benefit.

Size

No magnitude yet: distribution is not documented.

Compared with

Citizen calls for service about shots fired in Kansas City. Measured.

Without the system
390.87 s to arrive on scene, stopping 54.62 m from the gunfire
With it
266.82 s to arrive on scene, stopping 35.66 m from the gunfire
The system’s part
The evaluation compared responses to alerts with responses to citizen calls and compared covered areas and incidents with weighted controls, so it isolates the system's part in the procedural gains. The system includes acoustic experts who confirm each alert, and the report does not separate the classifier from the reviewers.
Learns from data

Shown. SoundThinking's product page says that audio from reviewed incidents is kept to train the machine learning model that filters detections. The evaluation report describes the sensors and the human review and does not describe the classifier.

“If an incident is created and sent to our Incident Review Center the short audio snippet is stored permanently for evidentiary purposes as well as to train the machine learning model.” Source

Not yet checked
LimitsCosts and harmsLater outcome

Download data Cite Suggest a correction

Benefit type
Reduced Task Time
System
ShotSpotter gunshot detection technology (GDT), with alerts confirmed at the Real-Time Incident Review Center
Made by
ShotSpotter, Inc. (renamed SoundThinking, Inc. in 2023)
Used by
Kansas City Police Department and Chicago Police Department
Where
Kansas City, Missouri and Chicago, Illinois, United States
Stage
In routine use
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Physical health, Operational improvement (crime reduction or prevention)
Collections
Scrutiny and findings
Last revised
1 November 2026

Sources

  1. Evaluation report, by authors with no tie to the system.

    Piza, Eric L., George O. Mohler, Jeremy G. Carter, David N. Hatten, Nathan T. Connealy, Rachael Arietti, Jisoo Cho and Emily Castillo. The Impact of Gunshot Detection Technology on Gun Violence in Kansas City and Chicago: A Multi-Pronged Evaluation. Final report to the National Institute of Justice, award 2019-R2-CX-0004, document 308357, January 2024.

    GDT seems to positively impact a number of procedural aspects of police response to gun fire. GDT further demonstrates a positive influence on evidence collection. Unfortunately, these procedural benefits did not translate to any meaningful improvements to crime control outcomes.
    NIBIN evidence collection was 30.4% higher in the GDT target area than the weighted control area.
    Firearms were 45% more likely to be recovered from fatal shooting incidents occurring within the GDT target area as compared to the control area.

  2. Other, by the makers. Context or contrary evidence.

    SoundThinking. ShotSpotter Gunshot Detection System, product page.

    If an incident is created and sent to our Incident Review Center the short audio snippet is stored permanently for evidentiary purposes as well as to train the machine learning model.

Details

AI system

Workflow

Acoustic sensors covered about 3.5 square miles of Kansas City from October 2012 and about 100 square miles of Chicago by May 2018. ShotSpotter's acoustic experts reviewed each detection before an alert went to police. Officers were dispatched to alerts as they were to citizen calls, and patrol-car locator data recorded their movements.

Follow-up

Conditions for replication

Sensors must cover the area where the gunfire occurs. Police must dispatch officers to the alerts and collect evidence at the scene.

Entry details

Sector

Policing (gunfire detection).

Purpose

ShotSpotter built its gunshot detection system to detect and locate outdoor gunfire with acoustic sensors and send police an alert for each confirmed incident.

30 more questions not yet checked

model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this benefit

Peter H. Vartanian. (2026). ShotSpotter got police to gunfire sooner, but crime did not fall (AIBD-1201). Artificial Intelligence Benefits Database, edition of 2 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1201.html (archived at https://doi.org/10.7910/DVN/AADSII, version 9.0)

BibTeX Data Field definitions