ShotSpotter Accuracy Debate Examined

By IPVM, Published Jun 25, 2021, 08:40am EDT

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 *******

*********** ****** **% ******** and ********** **% ******** in * ******** **** Springfield **, *** ******* false ****** **** ******** accuracy *** *********. **** also ****** **** *** unverified ****** *** ****. The ********* ******* ****** reports **** **% ** ShotSpotter ****** ** ******* from ****-**** *** *** result ** * **** report, ******** **** "*********** creates ********* ** ****-*** police *********** **** **** no ******** ** ****** gunfire". ******* ****, ******* continues ** ** ***********'* biggest ******** *** ******* Mayor **** ********* **** "ShotSpotter ***** ** ********* Role" ** ****** ******.

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

*********** ******* ***** ** to ** ******* *** square **** *** ******* detection. ***** * ****** picks ** *****, ********* along **** ***** ****** are **** ** ******** it ** * ******* or ***.

** *** *********** ******** for **%+ ** *********** 2020 *******. **** ****** having ***+ ****** ** customers. *** **** ** ShotSpotter's ******** ************** ********** *** ******** Examined

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

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

**’* ********* ** ***** out **** **% ** all ******** ****** *** nation *** *** ******** to *-*-*. *********** ****** help ** ***** ********* trust, ***** **** *****, enhances ******* ******, *** increases ******** **********.

**’* **** ********* ** point *** ****, ***** upon ******** ********, **** 0.5% ** *********** ****** as ********** ****** *** country *** ***** ********.

** *** *********** ******, an ***** ** ****** a “***** ********” ***** when *********** ****** *** enforcement ** **** ** determines ** * *******, police *** ******** ** the ******** ** *** alert, *** **** ******* the ***** *** ********* else – ****** ******** of ********* *** *******.

***********’* **** ********* ******* steps ** ****** **** if ****** ******** ******** the *********** ***** *** indeed * “***** ********,” they ****** **** ** our **** ** ** can **** ***** *** take ******** ***** ** minimize ***** ********* ** the ******.

**** ******** ** ***********: "Does *********** **** ** bullets ******* **** .** caliber? ** ***** * minimum ******** ******* ** the ********** **% ** larger *******?"

*********** ********** **** **% of ************, ******* ******* incidents, ***** ********, ************ available ****** ******* **** .25 *******, ****** *** Coverage **** **** ** detected *** ******* ****** 25 ****** ** *** actual *******.

**** ******** ** ***********: "Does *********** **** ******** to *** ** ******** to *** ********* ******* Center ****** ** ***** accuracy? * ******* *********** contends * **** ** a ****** ****** **** not **** * *** was *** *****, *** is ***** ******** ****?"

** **** **** *** customers **** *** *********** system ******* *** ********* of ** ***** **% detection ******** ******* ********* report ***** ********* ** negatives ******** ** *** company. **** ******* ** to **** ***** ** and ***** *** ******* level ********* ** **** as *********** ******* *** system. **** *** **** two ***** *********** *** maintained * **% ******** rate ********* * *.*% false ******** **** ********** across *** *********.

*** ****** ***** ********* conclusions **** ***** ************** of ****** ****** ***************, falsely ******** **** ** no ***** ***** *** therefore ***** *********. *********** has **** ** ********* for ** *****, ****** more **** *** ****** and *** ****** ***** and **** ******* ***** from **** ****** *********** because *** ****** ** effective ** ******* **** lives, ****** *** ********, and **** *********** *****. 911 **** ****** **** alone ******** ** ********** and ********** ******* ** ShotSpotter’s ******** *** *************.

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

*********** **** **** **** they ***** *** **** installations *** ** *** deploy **** ****** **** can ****** ******* **** 90% ******** ** ******:

*** **** **********, *********** rigorously ****** *** ***** every ********** ********* ******* alerts ** *** ******** review ******. *** ********* technicians *** **** ******** if **** *** **** to ****** ******* **** 90% ******** ** ******. Most ** ***********’* ********* outperform *** **% ******** requirement.

*********** **** ********* **** rely ** ********* ** report ***** *********:

*** ***** ** ***** positives ***** ** ***** a ***. *** **** background, *********** ****** ** its ********* ** ****** false *********, *** **** number ** ** ***** that ** ** *** a ******* *** **** customers.

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

*********** ********** **% ** outdoor ******* **** ****** greater **** .** ******* will ** ********, ***** ****** *********** ** contract **** ***********:

**% ** ************, ******* gunfire *********, ***** ********, commercially ********* ****** ******* than .** *******, ****** the ******** **** **** bedetected *** ******* ****** 25 ****** (** ****) of *** ****** ******* location.

**** ****** **** *** include ***** *********, **** fireworks ** ***** ****** that *** ****** ***** detect ** *******, ***** is * **** ********* from *** ********* ******* Center.

*******, *********** ******* ***** positives, **** ** ******** on ********* *** ***** loud ******, **** *********** accuracy ** **** ** their ********:

*** *********** ******* ****** will ******* **** *** correct ********* *** ******** location *** ****** ******* (90%) ** ********** (*******, unsuppressed) ********* ******* ***** occurs ****** * ******** area, *** “******** ****”, provided *** *********** ** Statistically ***********, ** ******* below. **** *********** **** shall ** ********** ** a ********** ** *******:

IPVM Image

***** *** “*********** ****” is * ****** ********* as * **********, “***********************” is *** ****** ** “Gunfire *********” ********* ****** the ******** **** ****** the ********* ****** *** which *** *********** ******** an ******** ********, **************** is *** ****** ** Verified ********* (* “******** Incident” ** ** ******** where ******** *** ******** or ***** ******** ******** that ******* **** *****) for ***** *** *********** produced ** ********** ******** (i.e., * ********** ********), and ***************** ** *** number ** ******** ********* for ***** *** *********** failed ** ****** * location ** *** (*.*., Missed *********).

*** *********** *********** **** only ********* *********** ** they **** ** ******** an ****** ******* (*****************) or **** ****** ** in *** ***** ******** (NumberMislocated).

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

*********** *** * ************ method *** ******** ***** positives **** **** ****** them ** *** ****** verify **** *** ****** noise ****** ***, ** they ********* ** **:

** *** *********** ******, an ***** ** ****** a “***** ********” ***** when *********** ****** *** enforcement ** **** ** determines ** * *******, police *** ******** ** the ******** ** *** alert, *** **** ******* the ***** *** ********* else – ****** ******** of ********* *** *******.

*** ******* ** **** a ***********, ****** ************, number ** ****** *** never ******** ** ** what *** ****** ** the ***** ***. ** such, **** *** ********** alerts *** ******** **** being ***** ** ********** and **** **** ** overstated ********.

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

** *******, **% ** ~40,000 *********** ****** *** to ** ***** *************** ** *** ********* Justice ******** ************ **********’* ****** of ***. **** ********** this ***** ** **** from *** **** ** Chicago, ***********'* ******* ********. The ********* ******* ****** says *** **** ** case ******* ***** **** "ShotSpotter ******* ********* ** dead-end ****** *********** **** find ** ******** ** actual *******"

IPVM Image

*********** **** **** **** the ****** ** ********** because ** ** ******** a **** ** * police ****** **** * false ********:

*** ****** ***** ********* conclusions **** ***** ************** of ****** ****** ***************, falsely ******** **** ** no ***** ***** *** therefore ***** *********. [...] 911 **** ****** **** alone ******** ** ********** and ********** ******* ** ShotSpotter’s ******** *** *************.

***** ** ** **** that **** ****** ***** be **** **** ** a **** ****** *** not *****, *** **** of * **** ****** signals **** ***** *** no ******* ** *** public *** *** **** of *** ****** ********** to ***** *****.

*** ****** ********** **** this ***** ** ************** deployments:

*** **** ** ******* has ******** *********** ** 12 ****** *********. ***** districts *** *** **** with *** ******* ********** of ***** *** ****** residents ** *** ****. ShotSpotter ******* ********* ** the ***** *** **** sides **** ********* ** high-intensity *********** ***** ****** are ******* *** ******** gunfire ** ****.

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

*********** **** *********** *** based ** ***** ***-******* crime ***** *** *******:

***** **** **** ***** and ***-***** *********, **** governments *** ****** *********** determine ***** ***-******* ***** rates *** *** *******. This *********** ** **** to ******** *** ********** where *********** ******* **** be **** ******* ** driving **** ***-******* ******** ****** ************* *****.

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

*** **** ** ******* Office ** ********* ******* (OIG)******** * ******** ****** **, **** analyzing *** ******* ****** Department’s (***) *** ** ShotSpotter ******* ******* *, 2020 *** *** **, 2021, *** ***** **** it ****** *** ** evidence ** *** ****** or ************* *****:

**** ************ ******** ** ShotSpotter **** *** ***** records, *** ********* **** CPD ********* ** *********** alerts ****** ******* ******** of * ***-******* *****, rarely **** **** ** investigatory *****, *** **** less ********** **** ** the ******** ** *** crime-related ******** ****** ** investigatory ****.

** ********, *********** **** IPVM *** ***** *** not ******* ***********’* ******** and **** *** ********* ShotSpotter “** ** ********* part ** ***** **********”:

** ** ********* ** point *** **** *** Chicago ****** ********** *********** describes *********** ** ** important **** ** ***** operations. *** *** ****** does *** ********** ******* on ***********’* ******** ***** has **** ************* ******* at ** ******* ***** on ******** **** **** than *** *********. *** does *** *** ******* that *********** ****** *** not ********** ** ****** gunfire ******* ** *** physical ******** ** *********. We ***** ***** ** the ******* ****** ********** to ******* ** *** value *** ********** **** from ***** **** ** precisely ******* ** ******** incidents ** *******. ** work **** ******* **** our ****** ********* ** ensure **** *** ******* value *** ** *** service.

Scientific *******

*** ****** **** ******* that *********** *** ** scientific ******* ******* *** performance:

*********** *** ***** **** a ************** ***** ***** to ********* ******* *** system *** ******** **** the ********** ******* *** sound ** ******* *** other **** ****** **** firecrackers, **** **********, ************ noises, ***********, *** ***** harmless ******.

**** *** *** ***** any **** ***** ********** ShotSpotter.

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

*******, *******'* ***** ******* ShotSpotter *** *** **** remains ***** ******* ********, signaling **** ******* ** satisfied **** *** ***** of ******** **** *******. Chicago ***** **** ********* said "*********** ***** ** important ****" ** ****** lives,********* ** ******. ******* **** ********* to *** ~$* ******* a **** *** ***********, showing **** **** ***** the ******* **** *******.

Accuracy ******

***** *** ****** **** does *** ****** * definitive ********** ** ***** alerts, *** ***** ******** problem ** ****** ************* greater **** **** *********** insinuates. *********** **** ********** assumptions *** * ********** accuracy *********** *** ***** advertised *** ********** ******** rates. **** **** **** to ** *********** ** accuracy *** ** ************* of ***** ********* ***** can ***** ****** ********* and ***** *** ********** of ***********'* ********. *******, on *** ********* ****** side, ***** **** ********* be **** ***** ** actual ******* **** ** not **** ** * police ****** *** *** question ** *** **** of ***** *** *** case.

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

***** ***** ****** **** significant ******* **** ******* may ******* ********** ********, smaller ****** **** ***** crime ***** *** ***. Because ******** *** **** an ********* ******* ** cities **** *******, **** if */* ****** *** false *********** *** ***** be ********** ** ***** cities. ***, ******, ***** gun ******** ** *** as *** ** ***** as *******, **** ****** have * ****** ********** of ***** ****** ******* there *** ***** **** gunshots *** **** *** less ******* *** ******* operational ***** ** ****** officers ******* ** ************** false ******.

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":

**** ** **********. **’* important ** ********* **** smaller ****** **** **** incidents ** ******* *** therefore *** **** ** more ****** ********. *********** has **** * ******* group ** ******* ****** seeing *** ***** ** ShotSpotter. *********** ** ******* them ******** ******** **** they ***** ********* *** have ***** ***** ***** helps ****** ** ******* and **** *****.

Comments (12)

********* ** ** ******* in *******, *** **** is ** ******** **** of ***** *** **********. Just ***** ** *** it *** ***** **** police *** ****** ****** "differently" ** **** ****'* able ** **** **** crimes *** ** ******** higher ** ***** *** numbers *** ** **** their ***. ** *** same *****, ***** ***** be **** **** **** reasons *** ***** ***** ShotSpotter ** ****.

Agree: 2
Disagree
Informative
Unhelpful
Funny

*********** *** **** ** Chicago *** ****** * decade ***, ********* *** only **** ***** ***** 2019.

* ****'* *** **** mentioned ** *** *******, but ** ********** ****** **% ******* to * **** ** 5,600 ***** ********. ** may **** ** * useful ************* **** *** them, ********* **** ******** date *** **** *********** than ** ********** ******* even **** *********** ***'* the **** ********* *** a ****.

* ***** **** ***********, does *********** ***** ****** also ******* **** ** officers ******* ** ******* to ***** *****/******? ** no, **** *** * question ** **** ***** do *** ***** *** benefits *******, *** ******* is ******** *********, *** is ** ***** *** price. ********* ** *** though ** ********* *****'* look ***** *** *********** from ***** * *****.

Agree
Disagree
Informative: 2
Unhelpful
Funny

**** ***** ******* ********* to ************. *** *** graph ******** **% ** reports *** *** *****, says **** ******* *** filed ** *** *** itself.

IPVM Image

*** *** ***** ***, I *** ** **** video ** ** ******** where * ****** ***** said "****** *******".

Agree: 2
Disagree
Informative
Unhelpful: 1
Funny: 1

***** *** *** ******** that ** *** *********. I **** ******* *** image ** **** ** clear **** **% ** alerts *** *** ****** in * **** ****** being ***** ** *** police********* ** *** ********* Research ******.

Agree
Disagree
Informative
Unhelpful
Funny

**’* ********* ** ***** out **** **% ** all ******** ****** *** nation *** *** ******** to *-*-*. *********** ****** help ** ***** ********* trust, ***** **** *****, enhances ******* ******, *** increases ******** **********.

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

***** ***** ** ***** stagnation, **** ******* ****************** ** ****** ***** ago ** **** ***** wares *************** ** ****** - and ** ***** ** have ****** **** ** a ********, ******* ***** growth **** ***.

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

***** *** *****'*******' ****... **'* ** ******** assault ** ************ ******* and *********** **** ****** to ** ******** ********* to **** ** ***** claims.

**** **** ***** *** percentage ** "***** *****' and "********** ** *********" as ** ***** ******* are ********** ***** **** can ** **** ** the *** ** ***** products - ***** ** course, **** *** ***.

**** ** **** '**% of *** ******** ****** the ****** *** *** reported ** *-*-*' ***** that * **** ****** thought *** ******** ********.

**** ** **** **** show ** ******** ** back ** ***** *****: an ****** ********* ********* study **** **** (* underlined *** **** ****)

IPVM Image

Agree
Disagree
Informative: 2
Unhelpful
Funny

*** **** ********* **** list ** *** ****** of ***** ******* **** is ** ********:

IPVM Image

**** ** ******** '******** new *******' ********* ****-****.

Agree: 1
Disagree
Informative
Unhelpful
Funny: 1

* ****** *** ***** is * ***** ** the ***********... *** *% of "***********" ** *** take?

Agree
Disagree
Informative
Unhelpful
Funny

******:** **** ******* **** report ** ******* ******** from ***********.

*********** **** **** **** train *** **** ************* and ** *** ****** them ****** **** *** detect ******* **** **% accuracy ** ******:

*** **** **********, *********** rigorously ****** *** ***** every ********** ********* ******* alerts ** *** ******** review ******. *** ********* technicians *** **** ******** if **** *** **** to ****** ******* **** 90% ******** ** ******. Most ** ***********’* ********* outperform *** **% ******** requirement.

*********** **** ********* **** they **** ** ********* to ****** ***** *********:

*** ***** ** ***** positives ***** ** ***** a ***. *** **** background, *********** ****** ** its ********* ** ****** false *********, *** **** number ** ** ***** that ** ** *** a ******* *** **** 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":

**** ** **********. **’* important ** ********* **** smaller ****** **** **** incidents ** ******* *** therefore *** **** ** more ****** ********. *********** has **** * ******* group ** ******* ****** seeing *** ***** ** ShotSpotter. *********** ** ******* them ******** ******** **** they ***** ********* *** have ***** ***** ***** helps ****** ** ******* and **** *****.

Agree
Disagree
Informative
Unhelpful
Funny

*** **** **********, *********** rigorously ****** *** ***** every ********** ********* ******* alerts ** *** ******** review ******. *** ********* technicians *** **** ******** if **** *** **** to ****** ******* **** 90% ******** ** ******. Most ** ***********’* ********* outperform *** **% ******** requirement.

**** **** *** *********** 'detection ***********' ******** ************* process **** ****?

** ***** * '***' somewhere ** ***** **** bring ******** ** **** has ********** ** ****** and ************ ** **** serious-minded ****** ******* ** tell *** ********** ******* two ****** ******* ******** and * *******?

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

Agree: 1
Disagree
Informative
Unhelpful
Funny

*********** ****** ****** **** - ***** ********** ** shot ******* ** ******** altering ******** ...****** *** ******* *********** to ***** ******** **** Gunshot-Detecting **

Agree
Disagree
Informative
Unhelpful
Funny

***.

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

*** ***** *** **:** p.m. ***** **** **, a *********** ******* ******** overrode *** ********** *** “reclassified” *** ***** ** a *******. ****, ****** later *** ***** “****-**********,” another *********** ******* ******* the *****’* *********** ** a ******** ** ***** Stony ****** ***** **** where ********’ *** *** seen ** ******.

** *** ** **** what **** ** ******* is ****** ** ***** detection ********** ******** ************* course - **** ** alter **** **** *** cops ***** **'* ***** - ** *****'* *** the ************* *********. *** nice.

****** **** ****** ***********’* technology *** *** *********' actions ** * **** hearing, *** *********** ******** all *********** ******** ******* Williams.

*** ******* **** *** wish ** **** *** kind ** ********* ******** of *** *** *******.

Agree: 1
Disagree
Informative: 3
Unhelpful
Funny

**** ****** **** * system * ***** **** used ** *********** *** fate ** * ****** human...

********** ***** ** **** log **** *********** *** changes! ********* *** *** changes, *** *** **** the **** ********** *** the ********* *********.

Agree
Disagree
Informative
Unhelpful
Funny
Read this IPVM report for free.

This article is part of IPVM's 7,270 reports and 968 tests and is only available to subscribers. To get a one-time preview of our work, enter your work email to access the full article.

Already a subscriber? Login here | Join now
Loading Related Reports