This article is no longer available publicly. Please subscribe to read.

ShotSpotter Accuracy Debate Examined

Published Jun 25, 2021 12:40 PM

Is ShotSpotter, the widely used and widely criticized gunshot detection system, accurate or not? This has become a heated debate in Chicago with Northwestern Law School finding that nearly 90% of alerts are not gun-related incidents while ShotSpotter claims 97% aggregated accuracy. Who is right?

IPVM Image

IPVM explains both sides, explains how ShotSpotter calculates their accuracy, analyzing the limitations and possible flaws in both and how this can impact city usage of a gunshot detection system.

Update June 30th, 2021: ShotSpotter sent IPVM responses to this article that we have added.

Executive *******

*********** ****** **% ******** *** ********** 90% ******** ** * ******** **** Springfield **, *** ******* ***** ****** when ******** ******** *** *********. **** also ****** **** *** ********** ****** are ****. *** ********* ******* ****** reports **** **% ** *********** ****** in ******* **** ****-**** *** *** result ** * **** ******, ******** that "*********** ******* ********* ** ****-*** police *********** **** **** ** ******** of ****** *******". ******* ****, ******* continues ** ** ***********'* ******* ******** and ******* ***** **** ********* **** "ShotSpotter ***** ** ********* ****" ** public ******.

ShotSpotter ******* ********* ********

*********** ******* ***** ** ** ** sensors *** ****** **** *** ******* detection. ***** * ****** ***** ** noise, ********* ***** **** ***** ****** are **** ** ******** ** ** a ******* ** ***.

** *** *********** ******** *** **%+ of *********** **** *******. **** ****** having ***+ ****** ** *********. *** more ** ***********'* ******** ************** ********** *** ******** ********

ShotSpotter ******** ** **** ** ********

**** ******** ** ***********:"Does *********** **** ***** ** ***** ****** ** ****** ** **** *** ******* *** *** ****** **** *** ** ******* *************?"

**’* ********* ** ***** *** **** 88% ** *** ******** ****** *** nation *** *** ******** ** *-*-*. ShotSpotter ****** **** ** ***** ********* trust, ***** **** *****, ******** ******* safety, *** ********* ******** **********.

**’* **** ********* ** ***** *** that, ***** **** ******** ********, **** 0.5% ** *********** ****** ** ********** across *** ******* *** ***** ********.

** *** *********** ******, ** ***** is ****** * “***** ********” ***** when *********** ****** *** *********** ** what ** ********** ** * *******, police *** ******** ** *** ******** of *** *****, *** **** ******* the ***** *** ********* **** – seeing ******** ** ********* *** *******.

***********’* **** ********* ******* ***** ** ensure **** ** ****** ******** ******** the *********** ***** *** ****** * “false ********,” **** ****** **** ** our **** ** ** *** **** track *** **** ******** ***** ** minimize ***** ********* ** *** ******.

**** ******** ** ***********: "**** *********** work ** ******* ******* **** .** caliber? ** ***** * ******* ******** similar ** *** ********** **% ** larger *******?"

*********** ********** **** **% ** ************, outdoor ******* *********, ***** ********, ************ available ****** ******* **** .** *******, inside *** ******** **** **** ** detected *** ******* ****** ** ****** of *** ****** *******.

**** ******** ** ***********: "**** *********** have ******** ** *** ** ******** to *** ********* ******* ****** ****** on ***** ********? * ******* *********** contends * **** ** * ****** report **** *** **** * *** was *** *****, *** ** ***** anything ****?"

** **** **** *** ********* **** the *********** ****** ******* *** ********* of ** ***** **% ********* ******** because ********* ****** ***** ********* ** negatives ******** ** *** *******. **** enables ** ** **** ***** ** and ***** *** ******* ***** ********* as **** ** *********** ******* *** system. **** *** **** *** ***** ShotSpotter *** ********** * **% ******** rate ********* * *.*% ***** ******** rate ********** ****** *** *********.

*** ****** ***** ********* *********** **** their ************** ** ****** ****** ***************, falsely ******** **** ** ** ***** fired *** ********* ***** *********. *********** has **** ** ********* *** ** years, ****** **** **** *** ****** and *** ****** ***** *** **** renewal ***** **** **** ****** *********** because *** ****** ** ********* ** helping **** *****, ****** *** ********, and **** *********** *****. *** **** center **** ***** ******** ** ********** and ********** ******* ** ***********’* ******** and *************.

Updates **** *********** ** ********

*********** **** **** **** **** ***** and **** ************* *** ** *** deploy **** ****** **** *** ****** gunfire **** **% ******** ** ******:

*** **** **********, *********** ********** ****** and ***** ***** ********** ********* ******* alerts ** *** ******** ****** ******. The ********* *********** *** **** ******** if **** *** **** ** ****** gunfire **** **% ******** ** ******. Most ** ***********’* ********* ********** *** 90% ******** ***********.

*********** **** ********* **** **** ** customers ** ****** ***** *********:

*** ***** ** ***** ********* ***** up ***** * ***. *** **** background, *********** ****** ** *** ********* to ****** ***** *********, *** **** number ** ** ***** **** ** is *** * ******* *** **** customers.

Contract ******** ******

*********** ********** **% ** ******* ******* with ****** ******* **** .** ******* will ** ********, ***** ****** *********** ** ******** **** ShotSpotter:

**% ** ************, ******* ******* *********, using ********, ************ ********* ****** ******* than .** *******, ****** *** ******** Area **** ********** *** ******* ****** 25 ****** (** ****) ** *** actual ******* ********.

**** ****** **** *** ******* ***** positives, **** ********* ** ***** ****** that *** ****** ***** ****** ** gunfire, ***** ** * **** ********* from *** ********* ******* ******.

*******, *********** ******* ***** *********, **** as ******** ** ********* *** ***** loud ******, **** *********** ******** ** seen ** ***** ********:

*** *********** ******* ****** **** ******* data *** ******* ********* *** ******** location *** ****** ******* (**%) ** detectable (*******, ************) ********* ******* ***** occurs ****** * ******** ****, *** “Coverage ****”, ******** *** *********** ** Statistically ***********, ** ******* *****. **** performance **** ***** ** ********** ** a ********** ** *******:

IPVM Image

***** *** “*********** ****” ** * number ********* ** * **********, “***********************” is *** ****** ** “******* *********” occurring ****** *** ******** **** ****** the ********* ****** *** ***** *** ShotSpotter ******** ** ******** ********, **************** is *** ****** ** ******** ********* (a “******** ********” ** ** ******** where ******** *** ******** ** ***** credible ******** **** ******* **** *****) for ***** *** *********** ******** ** inaccurate ******** (*.*., * ********** ********), and ***************** ** *** ****** ** Verified ********* *** ***** *** *********** failed ** ****** * ******** ** all (*.*., ****** *********).

*** *********** *********** **** **** ********* ShotSpotter ** **** **** ** ******** an ****** ******* (*****************) ** **** detect ** ** *** ***** ******** (NumberMislocated).

Only ****** ** ***** ** ******** **** ** *** ********

*********** *** * ************ ****** *** counting ***** ********* **** **** ****** them ** *** ****** ****** **** the ****** ***** ****** ***, ** they ********* ** **:

** *** *********** ******, ** ***** is ****** * “***** ********” ***** when *********** ****** *** *********** ** what ** ********** ** * *******, police *** ******** ** *** ******** of *** *****, *** **** ******* the ***** *** ********* **** – seeing ******** ** ********* *** *******.

*** ******* ** **** * ***********, though ************, ****** ** ****** *** never ******** ** ** **** *** source ** *** ***** ***. ** such, **** *** ********** ****** *** excluded **** ***** ***** ** ********** and **** **** ** ********** ********.

"Thousands ** ****-*** ****** ***********"

** *******, **% ** ~**,*** *********** alerts *** ** ** ***** *************** ** *** ********* ******* ******** ************ **********’* ****** ** ***. They ********** **** ***** ** **** from *** **** ** *******, ***********'* biggest ********. *** ********* ******* ****** says *** **** ** **** ******* shows **** "*********** ******* ********* ** dead-end ****** *********** **** **** ** evidence ** ****** *******"

IPVM Image

*********** **** **** **** *** ****** is ********** ******* ** ** ******** a **** ** * ****** ****** with * ***** ********:

*** ****** ***** ********* *********** **** their ************** ** ****** ****** ***************, falsely ******** **** ** ** ***** fired *** ********* ***** *********. [...] 911 **** ****** **** ***** ******** an ********** *** ********** ******* ** ShotSpotter’s ******** *** *************.

***** ** ** **** **** **** alerts ***** ** **** **** ** a **** ****** *** *** *****, the **** ** * **** ****** signals **** ***** *** ** ******* to *** ****** *** *** **** of *** ****** ********** ** ***** calls.

*** ****** ********** **** **** ***** to ************** ***********:

*** **** ** ******* *** ******** ShotSpotter ** ** ****** *********. ***** districts *** *** **** **** *** highest ********** ** ***** *** ****** residents ** *** ****. *********** ******* residents ** *** ***** *** **** sides **** ********* ** ****-********* *********** where ****** *** ******* *** ******** gunfire ** ****.

ShotSpotter's ******** ** **********:

*********** **** *********** *** ***** ** where ***-******* ***** ***** *** *******:

***** **** **** ***** *** ***-***** shootings, **** *********** *** ****** *********** determine ***** ***-******* ***** ***** *** the *******. **** *********** ** **** to ******** *** ********** ***** *********** sensors **** ** **** ******* ** driving **** ***-******* ******** – ****** neighborhoods *****.

Update: ******* ********* *******'* ******

*** **** ** ******* ****** ** Inspector ******* (***)******** * ******** ****** **, **** ********* *** Chicago ****** **********’* (***) *** ** ShotSpotter ******* ******* *, **** *** May **, ****, *** ***** **** it ****** *** ** ******** ** gun ****** ** ************* *****:

**** ************ ******** ** *********** **** and ***** *******, *** ********* **** CPD ********* ** *********** ****** ****** produce ******** ** * ***-******* *****, rarely **** **** ** ************* *****, and **** **** ********** **** ** the ******** ** *** *****-******* ******** during ** ************* ****.

** ********, *********** **** **** *** study *** *** ******* ***********’* ******** and **** *** ********* *********** “** an ********* **** ** ***** **********”:

** ** ********* ** ***** *** that *** ******* ****** ********** *********** describes *********** ** ** ********* **** of ***** **********. *** *** ****** does *** ********** ******* ** ***********’* accuracy ***** *** **** ************* ******* at ** ******* ***** ** ******** from **** **** *** *********. *** does *** *** ******* **** *********** alerts *** *** ********** ** ****** gunfire ******* ** *** ******** ******** is *********. ** ***** ***** ** the ******* ****** ********** ** ******* to *** ***** *** ********** **** from ***** **** ** ********* ******* to ******** ********* ** *******. ** work **** ******* **** *** ****** customers ** ****** **** *** ******* value *** ** *** *******.

Scientific *******

*** ****** **** ******* **** *********** has ** ********** ******* ******* *** performance:

*********** *** ***** **** * ************** valid ***** ** ********* ******* *** system *** ******** **** *** ********** between *** ***** ** ******* *** other **** ****** **** ************, **** backfiring, ************ ******, ***********, *** ***** harmless ******.

**** *** *** ***** *** **** study ********** ***********.

"ShotSpotter ***** ** ********* ****" - ******* ***** **** *********

*******, *******'* ***** ******* *********** *** the **** ******* ***** ******* ********, signaling **** ******* ** ********* **** the ***** ** ******** **** *******. Chicago ***** **** ********* **** "*********** plays ** ********* ****" ** ****** lives,********* ** ******. ******* **** ********* ** *** ~$8 ******* * **** *** ***********, showing **** **** ***** *** ******* they *******.

Accuracy ******

***** *** ****** **** **** *** enable * ********** ********** ** ***** alerts, *** ***** ******** ******* ** likely ************* ******* **** **** *********** insinuates. *********** **** ********** *********** *** a ********** ******** *********** *** ***** advertised *** ********** ******** *****. **** will **** ** ** *********** ** accuracy *** ** ************* ** ***** positives ***** *** ***** ****** ********* and ***** *** ********** ** ***********'* software. *******, ** *** ********* ****** side, ***** **** ********* ** **** cases ** ****** ******* **** ** not **** ** * ****** ****** but *** ******** ** *** **** of ***** *** *** ****.

Value **** ** **********

***** ***** ****** **** *********** ******* like ******* *** ******* ********** ********, smaller ****** **** ***** ***** ***** may ***. ******* ******** *** **** an ********* ******* ** ****** **** Chicago, **** ** */* ****** *** false *********** *** ***** ** ********** to ***** ******. ***, ******, ***** gun ******** ** *** ** *** an ***** ** *******, **** ****** have * ****** ********** ** ***** alerts ******* ***** *** ***** **** gunshots *** **** *** **** ******* and ******* *********** ***** ** ****** officers ******* ** ************** ***** ******.

Update: *********** **** **** *** ********** ** ***** ******

** ******** **“But, ****** ***** *** ******** ** *** ** *** ** ***** ** *******, **** ****** **** * ****** ********** ** ***** ****** ******* ***** *** ***** **** ******** *** **** *** **** ******* *** ******* *********** ***** ** ****** ******** ******* ** ************** ***** ******.” ShotSpotter says their data will have a larger impact because these cities have less crime and that there is an increase in "smaller cities seeing the value of ShotSpotter":

**** ** **********. **’* ********* ** recognize **** ******* ****** **** **** incidents ** ******* *** ********* *** data ** **** ****** ********. *********** has **** * ******* ***** ** smaller ****** ****** *** ***** ** ShotSpotter. *********** ** ******* **** ******** gunshots **** **** ***** ********* *** have ***** ***** ***** ***** ****** to ******* *** **** *****.

Comments (12)
UI
Undisclosed Integrator #1
Jun 25, 2021

********* ** ** ******* ** *******, the **** ** ** ******** **** of ***** *** **********. **** ***** to *** ** *** ***** **** police *** ****** ****** "***********" ** they ****'* **** ** **** **** crimes *** ** ******** ****** ** wants *** ******* *** ** **** their ***. ** *** **** *****, there ***** ** **** **** **** reasons *** ***** ***** *********** ** much.

(2)
UE
Undisclosed End User #4
Jun 28, 2021

*********** *** **** ** ******* *** nearly * ****** ***, ********* *** only **** ***** ***** ****.

* ****'* *** **** ********* ** the *******, *** ** ********** ****** **% ******* ** * case ** *,*** ***** ********. ** may **** ** * ****** ************* tool *** ****, ********* **** ******** date *** **** *********** **** ** eyewitness ******* **** **** *********** ***'* the **** ********* *** * ****.

* ***** **** ***********, **** *********** false ****** **** ******* **** ** officers ******* ** ******* ** ***** calls/issues? ** **, **** *** * question ** **** ***** ** *** above *** ******** *******, *** ******* is ******** *********, *** ** ** worth *** *****. ********* ** *** though ** ********* *****'* **** ***** for *********** **** ***** * *****.

(2)
UI
Undisclosed Integrator #2
Jun 25, 2021

**** ***** ******* ********* ** ************. The *** ***** ******** **% ** reports *** *** *****, **** **** reports *** ***** ** *** *** itself.

IPVM Image

*** *** ***** ***, * *** an **** ***** ** ** ******** where * ****** ***** **** "****** per****".

(2)
(1)
(1)
ZS
Zach Segal
Jun 25, 2021
IPVM • IPVMU Certified

***** *** *** ******** **** ** our *********. * **** ******* *** image ** **** ** ***** **** 86% ** ****** *** *** ****** in * **** ****** ***** ***** by *** *************** ** *** ********* ******** ******.

U
Undisclosed #3
Jun 25, 2021

**’* ********* ** ***** *** **** 88% ** *** ******** ****** *** nation *** *** ******** ** *-*-*. ShotSpotter ****** **** ** ***** ********* trust, ***** **** *****, ******** ******* safety, *** ********* ******** **********.

***** **** *** ******** ** ***** reply ** **** ** ***foundation ** *** **** **** ***** ***** *********** to Chiefs of Police in U.S. cities - and it was their *** **** they used to **** ********** **** ***** (**** ** **** below).

***** ***** ** ***** **********, **** started ****************** ** ****** ***** *** ** sell ***** ***** *************** ** ****** - *** ** seems ** **** ****** **** ** a ********, ******* ***** ****** **** off.

probable ******: ****** ** ****** **** ******** ******* **** **** *** ********* **** ***. *** ***********

***** *** *****'*******' ****... **'* ** ******** ******* ** unverifiable ******* *** *********** **** ****** to ** ******** ********* ** **** up ***** ******.

**** **** ***** *** ********** ** "Lives *****' *** "********** ** *********" as ** ***** ******* *** ********** facts **** *** ** **** ** the *** ** ***** ******** - which ** ******, **** *** ***.

**** ** **** '**% ** *** gunshots ****** *** ****** *** *** reported ** *-*-*' ***** **** * have ****** ******* *** ******** ********.

**** ** **** **** **** ** evidence ** **** ** ***** *****: an ****** ********* ********* ***** **** 2016 (* ********** *** **** ****)

IPVM Image

(2)
U
Undisclosed #3
Jun 26, 2021

*** **** ********* **** **** ** the ****** ** ***** ******* **** is ** ********:

IPVM Image

**** ** ******** '******** *** *******' marketing ****-****.

(1)
(1)
UI
Undisclosed Integrator #5
Jun 28, 2021

* ****** *** ***** ** * delta ** *** ***********... *** *% of "***********" ** *** ****?

ZS
Zach Segal
Jun 30, 2021
IPVM • IPVMU Certified

******:** **** ******* **** ****** ** include ******** **** ***********.

*********** **** **** **** ***** *** test ************* *** ** *** ****** them ****** **** *** ****** ******* with **% ******** ** ******:

*** **** **********, *********** ********** ****** and ***** ***** ********** ********* ******* alerts ** *** ******** ****** ******. The ********* *********** *** **** ******** if **** *** **** ** ****** gunfire **** **% ******** ** ******. Most ** ***********’* ********* ********** *** 90% ******** ***********.

*********** **** ********* **** **** **** on ********* ** ****** ***** *********:

*** ***** ** ***** ********* ***** up ***** * ***. *** **** background, *********** ****** ** *** ********* to ****** ***** *********, *** **** number ** ** ***** **** ** is *** * ******* *** **** customers.

** ******** **“But, ****** ***** *** ******** ** *** ** *** ** ***** ** *******, **** ****** **** * ****** ********** ** ***** ****** ******* ***** *** ***** **** ******** *** **** *** **** ******* *** ******* *********** ***** ** ****** ******** ******* ** ************** ***** ******.”ShotSpotter says their data will have a larger impact because these cities have less crime and that there is an increase in "smaller cities seeing the value of ShotSpotter":

**** ** **********. **’* ********* ** recognize **** ******* ****** **** **** incidents ** ******* *** ********* *** data ** **** ****** ********. *********** has **** * ******* ***** ** smaller ****** ****** *** ***** ** ShotSpotter. *********** ** ******* **** ******** gunshots **** **** ***** ********* *** have ***** ***** ***** ***** ****** to ******* *** **** *****.

U
Undisclosed #3
Jul 03, 2021

*** **** **********, *********** ********** ****** and ***** ***** ********** ********* ******* alerts ** *** ******** ****** ******. The ********* *********** *** **** ******** if **** *** **** ** ****** gunfire **** **% ******** ** ******. Most ** ***********’* ********* ********** *** 90% ******** ***********.

**** **** *** *********** '********* ***********' training ************* ******* **** ****?

** ***** * '***' ********* ** NoCal **** ***** ******** ** **** has ********** ** ****** *** ************ to **** *******-****** ****** ******* ** tell *** ********** ******* *** ****** clapped ******** *** * *******?

**** ** ****-****.

(1)
UM
Undisclosed Manufacturer #6
Jul 26, 2021

*********** ****** ****** **** - ***** inaccurate ** **** ******* ** ******** altering ******** ...****** *** ******* *********** ** ***** Evidence **** *******-********* **

U
Undisclosed #3
Jul 26, 2021

***.

**** **** ***** ****:

*** ***** *** **:** *.*. ***** came **, * *********** ******* ******** overrode *** ********** *** “************” *** sound ** * *******. ****, ****** later *** ***** “****-**********,” ******* *********** analyst ******* *** *****’* *********** ** a ******** ** ***** ***** ****** Drive **** ***** ********’ *** *** seen ** ******.

** *** ** **** **** **** of ******* ** ****** ** ***** detection ********** ******** ************* ****** - when ** ***** **** **** *** cops ***** **'* ***** - ** doesn't *** *** ************* *********. *** nice.

****** **** ****** ***********’* ********** *** its *********' ******* ** * **** hearing, *** *********** ******** *** *********** evidence ******* ********.

*** ******* **** *** **** ** have *** **** ** ********* ******** of *** *** *******.

(1)
(3)
UM
Undisclosed Manufacturer #7
Jul 26, 2021

**** ****** **** * ****** * would **** **** ** *********** *** fate ** * ****** *****...

********** ***** ** **** *** **** documenting *** *******! ********* *** *** changes, *** *** **** *** **** convenient *** *** ********* *********.