Al Algorit ithms & Explanatio ion: : A A Humble Framin ing - - PowerPoint PPT Presentation

al algorit ithms explanatio ion a a humble framin ing
SMART_READER_LITE
LIVE PREVIEW

Al Algorit ithms & Explanatio ion: : A A Humble Framin ing - - PowerPoint PPT Presentation

Al Algorit ithms & Explanatio ion: : A A Humble Framin ing Jeremy Heffner HunchLab Product Manager & Senior Data Scientist jheffner@azavea.com Predictive Policing Prevent Crime Design patrol allocations to minimize the predicted


slide-1
SLIDE 1

Al Algorit ithms & Explanatio ion: : A A Humble Framin ing

Jeremy Heffner HunchLab Product Manager & Senior Data Scientist jheffner@azavea.com

slide-2
SLIDE 2

Predictive Policing

slide-3
SLIDE 3

Prevent Crime

slide-4
SLIDE 4

Design patrol allocations to minimize the predicted preventable reported harm

slide-5
SLIDE 5
slide-6
SLIDE 6
slide-7
SLIDE 7
slide-8
SLIDE 8
slide-9
SLIDE 9
slide-10
SLIDE 10
slide-11
SLIDE 11

“The more powerful you are, the more your actions will have an impact on people, the more responsible you are to act humbly.” Pope Francis

slide-12
SLIDE 12

Models make mistakes

slide-13
SLIDE 13
slide-14
SLIDE 14

Time Since Last & Theft From Vehicles (Seattle)

slide-15
SLIDE 15

Wind Speed & Aggravated Assault (Chicago)

slide-16
SLIDE 16

MVT and Distance from School (Philadelphia)

slide-17
SLIDE 17

Trade Secrets

slide-18
SLIDE 18

Is your creation that special that protecting it trumps the public interest? Likely no.

slide-19
SLIDE 19

Decision / Allocation Policy Explanations

slide-20
SLIDE 20
slide-21
SLIDE 21

# Assaults x 12 x 40% # Burglary x 8 x 60% # MVT x 5 x 65% # Larceny x 3 x 50% # Robbery x 10 x 40% Sum to Predicted Preventable Harm

slide-22
SLIDE 22
slide-23
SLIDE 23

Dealing with Uncertainty / Randomness

slide-24
SLIDE 24

101 100 2 2 2 50 1 1 1

slide-25
SLIDE 25

101 100 2 2 2 50 1 1 1

slide-26
SLIDE 26

75 30 2 2 2 60 1 1 1 101 100 2 2 2 50 1 1 1 80 60 2 2 2 40 1 1 1

slide-27
SLIDE 27

75 30 2 2 2 60 1 1 1 101 100 2 2 2 50 1 1 1 80 60 2 2 2 40 1 1 1

slide-28
SLIDE 28

This location was predicted to experience 0.01 robberies, 0.02 burglaries, … which represents 40 units of predicted preventable harm. This level of harm is 2 standard deviations above the mean, resulting in 4 lottery entries for this location. 5 locations were desired for patrol out of 11 eligible locations in the beat. Based upon the analysis, this location would be selected 83% of the time under the same conditions.

slide-29
SLIDE 29

10

slide-30
SLIDE 30

10 7

slide-31
SLIDE 31

10 7

slide-32
SLIDE 32

10 7

slide-33
SLIDE 33

10 7

slide-34
SLIDE 34

10 7

Acknowledges uncertainty Introduces randomness in explanation Preserves diversity in training examples

slide-35
SLIDE 35

Humans make mistakes

slide-36
SLIDE 36
slide-37
SLIDE 37

Jeremy Heffner HunchLab Product Manager & Senior Data Scientist jheffner@azavea.com www.hunchlab.com