In more than 140 cities, ShotSpotter’s artificial intelligence algorithm and network of microphones evaluate hundreds of thousands of sounds a year to determine if they are gunfire, generating data used in criminal cases nationwide.
A confidential ShotSpotter document obtained by The Associated Press outlines something the company doesn’t tout about its “precision policing system:” that employees can quickly overrule and reverse the algorithm’s determinations, and are given broad discretion to decide if a sound is a gunshot, fireworks, thunder or something else.
Such reversals happen 10 percent of the time, which could bring subjectivity into consequential decisions and conflict with one of the reasons AI is used in law-enforcement tools -- to lessen the role of all-too-fallible humans.
“I’ve listened to a lot of gunshot recordings — and it is not easy to do,” said Robert Maher, an authority on gunshot detection at Montana State University who reviewed the ShotSpotter document. “Sometimes it is obviously a gunshot. Sometimes it is just a ping, ping, ping. ... and you can convince yourself it is a gunshot.”
Marked “WARNING: CONFIDENTIAL,” the 19-page operations document spells out how employees in ShotSpotter’s review centers should listen to recordings and assess the algorithm’s finding of likely gunfire based on factors that may require judgment calls, including whether the sound has the cadence of gunfire, whether the audio pattern looks like “a sideways Christmas tree” and if there is “100% certainty of gunfire in reviewer’s mind.”
ShotSpotter said the human role is a positive check on the algorithm and the “plain-language” document reflects the high standards of accuracy its reviewers must meet.
“Our data, based on the review of millions of incidents, proves that human review adds value, accuracy and consistency to a review process that our customers—and many gunshot victims—depend on,” said Tom Chittum, the company’s vice president of analytics and forensic services.
Chittum said that the company’s expert witnesses have testified in 250 court cases in 22 states, and that its “97% aggregate accuracy rate for real-time detections across all customers” has been verified by an analytics firm the company commissioned.
The document underscores ShotSpotter’s longstanding emphasis on speed and decisiveness, and its commitment to classify sounds in less than a minute and alert local police and 911 dispatchers so they can send officers to the scene.
“You’re not giving your humans much time,” said Geoffrey Morrison, a voice-recognition scientist based in Britain who specializes in forensics processes. “And when humans are under great pressure, the possibility of mistakes is higher.”
ShotSpotter says it published 291,726 gunfire alerts to clients in 2021. The firm said more than 90 percent of the time its human reviewers agreed with the machine classification but the company invested in its team of reviewers “for the 10% of the time where they disagree with the machine.”