Prediction Officers - Improving resource allocation of the police force

[#1]

Team Name	Prediction Officers
Track	Public Sector
Use Case	We look to identify trends in police stops and explore possibilities of how we can manage allocation of police resources and personnel better.
Technology	SAS Viya, Python
Region	North America
Team lead	Sarik Koirala
Team members	@RaunakSengupta @anand_manivan @rafae
Social media handles
Is your team interested in participating in an interview?	Y
Optional: Expand on your technology expertise

Jury Video

​​​​​​​PredictionOfficers-CaseStudy-Jury.mp4

Video Player is loading.

Play Video

Play

Mute

Current Time 0:00

/

Duration 0:00

Loaded: 0%

0:00

Stream Type LIVE

Seek to live, currently behind liveLIVE

Remaining Time -0:00

1x

Playback Rate

Chapters

• Chapters

Descriptions

• descriptions off, selected

Captions

• captions settings, opens captions settings dialog
• captions off, selected

Audio Track

Picture-in-PictureFullscreen

This is a modal window.

Beginning of dialog window. Escape will cancel and close the window.

Text

ColorWhiteBlackRedGreenBlueYellowMagentaCyanTransparencyOpaqueSemi-Transparent

Background

ColorBlackWhiteRedGreenBlueYellowMagentaCyanTransparencyOpaqueSemi-TransparentTransparent

Window

ColorBlackWhiteRedGreenBlueYellowMagentaCyanTransparencyTransparentSemi-TransparentOpaque

Font Size

50%75%100%125%150%175%200%300%400%

Text Edge Style

NoneRaisedDepressedUniformDropshadow

Font Family

Proportional Sans-SerifMonospace Sans-SerifProportional SerifMonospace SerifCasualScriptSmall Caps

Reset restore all settings to the default valuesDone

Close Modal Dialog

End of dialog window.

Close Modal Dialog

This is a modal window. This modal can be closed by pressing the Escape key or activating the close button.

Pitch Video

​​​​​​​PredictionOfficers-CaseStudy-Pitch.mp4

Video Player is loading.

Play Video

Play

Mute

Current Time 0:00

/

Duration 0:00

Loaded: 0%

0:00

Stream Type LIVE

Seek to live, currently behind liveLIVE

Remaining Time -0:00

1x

Playback Rate

Chapters

• Chapters

Descriptions

• descriptions off, selected

Captions

• captions settings, opens captions settings dialog
• captions off, selected

Audio Track

Picture-in-PictureFullscreen

This is a modal window.

Beginning of dialog window. Escape will cancel and close the window.

Text

ColorWhiteBlackRedGreenBlueYellowMagentaCyanTransparencyOpaqueSemi-Transparent

Background

ColorBlackWhiteRedGreenBlueYellowMagentaCyanTransparencyOpaqueSemi-TransparentTransparent

Window

ColorBlackWhiteRedGreenBlueYellowMagentaCyanTransparencyTransparentSemi-TransparentOpaque

Font Size

50%75%100%125%150%175%200%300%400%

Text Edge Style

NoneRaisedDepressedUniformDropshadow

Font Family

Proportional Sans-SerifMonospace Sans-SerifProportional SerifMonospace SerifCasualScriptSmall Caps

Reset restore all settings to the default valuesDone

Close Modal Dialog

End of dialog window.

Close Modal Dialog

This is a modal window. This modal can be closed by pressing the Escape key or activating the close button.

[Atabarut]

Great case,

Probably you have taken a look at this? Building the future of modern policing | SAS

[Atabarut]

There is a great reading material here at the SAS blogs that I recommend How the police use analytics to disrupt fraud and scams - SAS Voices

which also includes a link to the nice whitepaper to download; Top tips for making the shift to evidence-based policing | SAS

[Atabarut]

A good paper from Turkey A33.pdf (itu.edu.tr) A Crime Prevention System in Spatiotemporal Principles With Repeat,
Near-Repeat Analysis and Crime Density Mapping: Case Study from Turkey, Trabzon

[rafae]

@Atabarut , thanks for the support. We will be happy to get feedback on our submissions

[LGroves]

Well done, Prediction Officers!  Policing, particularly equitable policing, is an important topic in the U.S.  Would love to hear if the decrease in traffic stops in 2019 was permanent, particularly with the confounding factor of COVID.  But, that's likely a story for another Hack 🙂

Nice work!

[rafae]

@LGroves , thanks for your comment. Here is our answer:

- the dramatic decrease in traffic stops started in 2018, so COVID was not a factor here. While we do not have data for the year 2020-2022 in the case of Nashville, we had data on Oklahoma City traffic stops up to the year 2020. For Oklahoma City, there was no such dramatic decrease in traffic stops in 2019 - 2020 (COVID years). It proves that COVID was not a confounding factor. 

In addition to this, based on the comparative study of other cities, racial disparity issue is present in the other cities as well, regardless of the level of diversity in those cities, geography, and political history. Oklahoma City (OK), San Francisco (CA), and Austin (TX) all show similar statistics. However, the Nashville case is important because the number of traffic stops was so high in Nashville and the dataset was so complete with different information that the dataset helped us to run analysis from various angles. 

Based on the comparative study, we strongly believe the authority/ govt. should pay ATTENTION to this issue. 

[LGroves]

Thank you for the added context, @rafae!  I also believe that this is an issue that needs a lot more attention and discussion.  So, thank you for including it as part of the 2023 SAS Hackathon - and, again, nice work on your project!