|
|
|
|
|
|
by sokoloff
844 days ago
|
|
|
If the false positive rate is 5%, it’s probably not much of a problem in terms of the overall balance of effectiveness. If the false positive rate is 95%, it’s pretty obviously going to be a diversion of police resources from whatever else they could be doing if not responding to zero-value alerts. |
|
|
This claims the false positive rate is under 3%. It's based on Shotspotter's statistics and "independent audit" statistics.
Not sure how trustworthy either is, but without better stats from anywhere else I have no reason to doubt the claim the false positive is pretty low.
Seems like even if false positive rate was at 50% it wouldn't be that big of a deal. Cities have police on patrol at all times anyway - it would just mean sending someone to drive 5 minutes away to see if there is visible a disturbance instead of them driving around the area they were currently randomly patrolling.