Anne Milgram: Why smart statistics are the key to fighting crime

221,744 views ใƒป 2014-01-28

TED


ืื ื ืœื—ืฅ ืคืขืžื™ื™ื ืขืœ ื”ื›ืชื•ื‘ื™ื•ืช ื‘ืื ื’ืœื™ืช ืœืžื˜ื” ื›ื“ื™ ืœื”ืคืขื™ืœ ืืช ื”ืกืจื˜ื•ืŸ.

ืชืจื’ื•ื: Michael Coslovsky ืขืจื™ื›ื”: Zeeva Livshitz
00:12
In 2007, I became the attorney general
0
12843
2591
ื‘-2007, ื”ืชืžื ื™ืชื™ ืœืคืจืงืœื™ื˜ืช ืžื“ื™ื ืช ื ื™ื• ื’'ืจื–ื™.
00:15
of the state of New Jersey.
1
15434
1725
00:17
Before that, I'd been a criminal prosecutor,
2
17159
2280
ืœืคื ื™ ื›ืŸ ื”ื™ื™ืชื™ ืชื•ื‘ืขืช ืคืœื™ืœื™ืช,
00:19
first in the Manhattan district attorney's office,
3
19439
2681
ื‘ืžืฉืจื“ ื”ืชื•ื‘ืข ื”ืžื—ื•ื–ื™ ื‘ืžื ื”ื˜ืŸ,
00:22
and then at the United States Department of Justice.
4
22120
2650
ื•ื‘ืžืฉืจื“ ื”ืžืฉืคื˜ื™ื ืฉืœ ืืจืฆื•ืช ื”ื‘ืจื™ืช.
00:24
But when I became the attorney general,
5
24770
2201
ืื‘ืœ ื›ืฉื ื”ื™ื™ืชื™ ืคืจืงืœื™ื˜ืช ื”ืžื“ื™ื ื”,
00:26
two things happened that changed the way I see criminal justice.
6
26971
3895
ืฉื ื™ ื“ื‘ืจื™ื ืฉื™ื ื• ืืช ื ืงื•ื“ืช ืžื‘ื˜ื™ ืขืœ ื”ืžืฉืคื˜ ื”ืคืœื™ืœื™.
00:30
The first is that I asked what I thought
7
30866
2030
ื”ืจืืฉื•ืŸ ื”ื™ื” ืฉืฉืืœืชื™ ืฉืืœื•ืช ืฉื ืจืื• ืœื™ ืžืžืฉ ื‘ืกื™ืกื™ื•ืช.
00:32
were really basic questions.
8
32896
2186
00:35
I wanted to understand who we were arresting,
9
35082
2856
ืจืฆื™ืชื™ ืœื”ื‘ื™ืŸ ืืช ืžื™ ืื ื—ื ื• ืขื•ืฆืจื™ื,
00:37
who we were charging,
10
37938
1664
ืืช ืžื™ ืื ื—ื ื• ืžืขืžื™ื“ื™ื ืœื“ื™ืŸ,
00:39
and who we were putting in our nation's jails
11
39602
2128
ื•ืืช ืžื™ ืื ื—ื ื• ืฉื•ืœื—ื™ื ืœื›ืœื.
00:41
and prisons.
12
41730
1416
00:43
I also wanted to understand
13
43146
1648
ืจืฆื™ืชื™ ื’ื ืœื”ื‘ื™ืŸ ืื ื”ื”ื—ืœื˜ื•ืช ืฉืื ื—ื ื• ืžืงื‘ืœื™ื ืžื’ื‘ื™ืจื•ืช ืืช ื”ื‘ื˜ื—ื•ืŸ ื”ืื™ืฉื™ ืฉืœื ื•.
00:44
if we were making decisions
14
44794
1329
00:46
in a way that made us safer.
15
46123
2518
00:48
And I couldn't get this information out.
16
48641
3252
ื•ืœื ื™ื›ื•ืœืชื™ ืœื”ืฉื™ื’ ืืช ื”ืžื™ื“ืข ื”ื–ื”.
00:51
It turned out that most big criminal justice agencies
17
51893
3357
ืžืกืชื‘ืจ ืฉืจื•ื‘ ืžืขืจื›ื•ืช ื”ื—ื•ืง, ื›ืžื• ื–ื• ืฉืœื™,
00:55
like my own
18
55250
1302
00:56
didn't track the things that matter.
19
56552
2382
ืœื ืขื•ืงื‘ื•ืช ืื—ืจื™ ื”ื“ื‘ืจื™ื ื”ื—ืฉื•ื‘ื™ื.
00:58
So after about a month of being incredibly frustrated,
20
58934
3318
ืื– ืื—ืจื™ ื—ื•ื“ืฉ ืฉืœ ืชืกื›ื•ืœ ื ื•ืจืื™,
01:02
I walked down into a conference room
21
62252
1971
ื ื›ื ืกืชื™ ืœื—ื“ืจ ื™ืฉื™ื‘ื•ืช ืฉื”ื™ื” ืžืœื ื‘ื‘ืœืฉื™ื ื•ื‘ืขืจื™ืžื•ืช ืฉืœ ืชื™ืงื™ื,
01:04
that was filled with detectives
22
64223
1890
01:06
and stacks and stacks of case files,
23
66113
2782
01:08
and the detectives were sitting there
24
68895
1176
ื•ื”ื‘ืœืฉื™ื ื™ืฉื‘ื• ืขื ืžื—ื‘ืจื•ืช ืฆื”ื•ื‘ื•ืช ื•ืจืฉืžื• ืœืขืฆืžื ื”ืขืจื•ืช.
01:10
with yellow legal pads taking notes.
25
70071
2234
01:12
They were trying to get the information
26
72305
1586
ื”ื ื ื™ืกื• ืœื”ืฉื™ื’ ืืช ื”ืžื™ื“ืข ืื•ืชื• ื—ื™ืคืฉืชื™
01:13
I was looking for
27
73891
1218
01:15
by going through case by case
28
75109
2045
ืขืœ ื™ื“ื™ ื‘ื“ื™ืงื” ืฉืœ ื›ืœ ืชื™ืง ื•ืชื™ืง ืžื—ืžืฉ ื”ืฉื ื™ื ื”ืื—ืจื•ื ื•ืช.
01:17
for the past five years.
29
77154
1898
01:19
And as you can imagine,
30
79052
1653
01:20
when we finally got the results, they weren't good.
31
80705
2643
ื•ื›ืคื™ ืฉืืคืฉืจ ืœื“ืžื™ื™ืŸ,
ื›ืฉืกื•ืฃ ืกื•ืฃ ืงื™ื‘ืœื ื• ืืช ื”ืžืžืฆืื™ื, ื”ื ืœื ื”ื™ื• ื˜ื•ื‘ื™ื.
01:23
It turned out that we were doing
32
83348
1655
ื”ืกืชื‘ืจ ืฉื”ืชืขืกืงื ื• ื”ืจื‘ื” ื‘ืขื‘ื™ืจื•ืช ืกืžื™ื ืžื“ืจื’ื” ื ืžื•ื›ื”,
01:25
a lot of low-level drug cases
33
85003
2020
01:27
on the streets just around the corner
34
87023
1475
ืฉื”ืชืจื—ืฉื• ื‘ืจื—ื•ื‘ื•ืช ืžืขื‘ืจ ืœืคื™ื ืช ื”ืžืฉืจื“ื™ื ืฉืœื ื•.
01:28
from our office in Trenton.
35
88498
2268
01:30
The second thing that happened
36
90766
1467
ื”ื“ื‘ืจ ื”ืฉื ื™ ืฉืงืจื” ื”ื•ื ืฉื‘ื™ืงืจืชื™ ื‘ืชื—ื ืช ื”ืžืฉื˜ืจื” ื‘ืงืžื“ืŸ ื‘ื ื™ื• ื’'ืจื–ื™.
01:32
is that I spent the day in the Camden, New Jersey police department.
37
92233
3674
01:35
Now, at that time, Camden, New Jersey,
38
95907
1887
ืขื›ืฉื™ื• ื‘ืื•ืชื” ืชืงื•ืคื” ืงืžื“ืŸ, ื ื™ื• ื’'ืจื–ื™ ื”ื™ื™ืชื” ื”ืขื™ืจ ื”ื›ื™ ืžืกื•ื›ื ืช ื‘ืืžืจื™ืงื”.
01:37
was the most dangerous city in America.
39
97794
2652
01:40
I ran the Camden Police Department because of that.
40
100446
3827
ื‘ื’ืœืœ ื–ื” ืื ื™ ื ื™ื”ืœืชื™ ืืช ืชื—ื ืช ืžืฉื˜ืจืช ืงืžื“ืŸ.
01:44
I spent the day in the police department,
41
104273
2112
ื‘ื™ืœื™ืชื™ ืืช ื”ื™ื•ื ื‘ืชื—ื ืช ื”ืžืฉื˜ืจื”,
01:46
and I was taken into a room with senior police officials,
42
106385
2726
ื•ืœืงื—ื• ืื•ืชื™ ืœื—ื“ืจ ืขื ืงืฆื™ื ื™ ืžืฉื˜ืจื” ื‘ื›ื™ืจื™ื,
01:49
all of whom were working hard
43
109111
1675
01:50
and trying very hard to reduce crime in Camden.
44
110786
3257
ืฉืขื‘ื“ื• ืงืฉื” ื•ื ื™ืกื• ื‘ืžืืžืฅ ืจื‘ ืœื”ื•ืจื™ื“ ืืช ืจืžืช ื”ืคืฉื™ืขื” ื‘ืงืžื“ืŸ.
01:54
And what I saw in that room,
45
114043
1826
ื•ืžื” ืฉืจืื™ืชื™ ื‘ืื•ืชื• ื—ื“ืจ,
01:55
as we talked about how to reduce crime,
46
115869
2245
ื‘ื–ืžืŸ ืฉื“ื™ื‘ืจื ื• ืขืœ ื”ื•ืจื“ืช ืจืžืช ื”ืคืฉื™ืขื”,
01:58
were a series of officers with a lot of little yellow sticky notes.
47
118114
3859
ื–ื” ื”ืจื‘ื” ืฉื•ื˜ืจื™ื ืขื ื”ืžื•ืŸ ืคืชืงื™ื•ืช ืฆื”ื•ื‘ื•ืช ื“ื‘ื™ืงื•ืช.
02:01
And they would take a yellow sticky and they would write something on it
48
121973
2846
ื•ื”ื ืœืงื—ื• ืคืชืงื™ืช ืฆื”ื•ื‘ื”, ืจืฉืžื• ืžืฉื”ื• ืขืœื™ื”, ื•ื”ื“ื‘ื™ืงื• ืื•ืชื” ืœืœื•ื—.
02:04
and they would put it up on a board.
49
124823
1799
02:06
And one of them said, "We had a robbery two weeks ago.
50
126622
2171
ื•ื‘ืคืชืง ืื—ื“ ื”ื™ื” ื›ืชื•ื‘: "ื”ื™ื” ืœื ื• ืฉื•ื“ ืœืคื ื™ ื›ืฉื‘ื•ืขื™ื™ื.
02:08
We have no suspects."
51
128793
1711
ืื™ืŸ ืœื ื• ื—ืฉื•ื“ื™ื."
02:10
And another said, "We had a shooting in this neighborhood last week. We have no suspects."
52
130504
5027
ื•ื‘ืื—ืจ: "ื”ื™ื” ืœื ื• ื™ืจื™ ื‘ืฉื›ื•ื ื” ื‘ืฉื‘ื•ืข ืฉืขื‘ืจ. ืื™ืŸ ืœื ื• ื—ืฉื•ื“ื™ื."
02:15
We weren't using data-driven policing.
53
135531
2583
ืœื ื”ืฉืชืžืฉื ื• ื‘ืฉื™ื˜ื•ืจ ืžื‘ื•ืกืก-ื ืชื•ื ื™ื.
02:18
We were essentially trying to fight crime
54
138114
2042
ื ื™ืกื™ื ื• ืœื”ื™ืœื—ื ื‘ืคืฉืข
02:20
with yellow Post-it notes.
55
140156
2527
ืขื ืคืชืงื™ื•ืช ื“ื‘ื™ืงื•ืช ื•ืฆื”ื•ื‘ื•ืช.
02:22
Now, both of these things made me realize
56
142683
2135
ืขื›ืฉื™ื•, ืฉื ื™ ื”ื“ื‘ืจื™ื ื”ืœืœื• ื’ืจืžื• ืœื™ ืœื”ื‘ื™ืŸ
02:24
fundamentally that we were failing.
57
144818
3251
ืฉื‘ืขืฆื, ืื ื—ื ื• ื ื›ืฉืœื™ื.
02:28
We didn't even know who was in our criminal justice system,
58
148069
3123
ืœื ื™ื“ืขื ื• ืืคื™ืœื• ืžื™ ื ืžืฆื ื‘ืžืขืจื›ืช ื”ืคืœื™ืœื™ืช ืฉืœื ื•,
02:31
we didn't have any data about the things that mattered,
59
151192
3235
ืœื ื”ื™ื• ืœื ื• ืฉื•ื ื ืชื•ื ื™ื ืขืœ ื”ื“ื‘ืจื™ื ื”ื—ืฉื•ื‘ื™ื,
02:34
and we didn't share data or use analytics
60
154427
2568
ื•ืœื ืฉื™ืชืคื ื• ื ืชื•ื ื™ื ืื• ื”ืฉืชืžืฉื ื• ื‘ื ื™ืชื•ื—ื™ื
02:36
or tools to help us make better decisions
61
156995
2151
ื›ื“ื™ ืœืงื‘ืœ ื”ื—ืœื˜ื•ืช ื˜ื•ื‘ื•ืช ื™ื•ืชืจ, ื•ืœื”ืคื—ื™ืช ืืช ืจืžืช ื”ืคืฉื™ืขื”.
02:39
and to reduce crime.
62
159146
2003
02:41
And for the first time, I started to think
63
161149
2224
ื•ืœืจืืฉื•ื ื” ื”ืชื—ืœืชื™ ืœื—ืฉื•ื‘ ืขืœ ื”ื“ืจืš ื‘ื” ืื ื—ื ื• ืžืงื‘ืœื™ื ื”ื—ืœื˜ื•ืช.
02:43
about how we made decisions.
64
163373
1910
02:45
When I was an assistant D.A.,
65
165283
1397
ื›ืฉื”ื™ื™ืชื™ ืขื•ื–ืจืช ื”ืชื•ื‘ืข ื”ืžื—ื•ื–ื™, ื•ื›ืฉื”ื™ื™ืชื™ ืชื•ื‘ืขืช ืคื“ืจืœื™ืช,
02:46
and when I was a federal prosecutor,
66
166680
1870
02:48
I looked at the cases in front of me,
67
168550
1746
ื”ื™ื™ืชื™ ืžืกืชื›ืœืช ื‘ืชื™ืงื™ื ืฉืœืคื ื™
02:50
and I generally made decisions based on my instinct
68
170296
2626
ื•ืžืงื‘ืœืช ื”ื—ืœื˜ื•ืช ื‘ื“ืจืš-ื›ืœืœ ืœืคื™ ื”ืื™ื ืกื˜ื™ื ืงื˜ ื•ื”ื ืกื™ื•ืŸ ืฉืœื™.
02:52
and my experience.
69
172922
1692
02:54
When I became attorney general,
70
174614
1659
ื›ืฉื ื”ื™ื™ืชื™ ืคืจืงืœื™ื˜ืช ื”ืžื“ื™ื ื”, ื™ื›ื•ืœืชื™ ืœื”ืกืชื›ืœ ืขืœ ื”ืžืขืจื›ืช ื‘ื›ืœืœื•ืชื”,
02:56
I could look at the system as a whole,
71
176273
1639
02:57
and what surprised me is that I found
72
177912
1818
ื•ืžื” ืฉื”ืคืชื™ืข ืื•ืชื™ ื–ื” ืฉื’ื™ืœื™ืชื™ ืฉืื ื—ื ื• ืขื•ื‘ื“ื™ื ื›ืš ื‘ืžืขืจื›ืช ื›ื•ืœื” -
02:59
that that was exactly how we were doing it
73
179730
1905
03:01
across the entire system --
74
181635
2303
03:03
in police departments, in prosecutors's offices,
75
183938
2401
ื‘ืชื—ื ื•ืช ืžืฉื˜ืจื”, ื‘ืžืฉืจื“ื™ ื”ืชื‘ื™ืขื”,
03:06
in courts and in jails.
76
186339
2800
ื‘ื‘ืชื™ ื”ืžืฉืคื˜ ื•ื‘ื‘ืชื™ ื”ืกื•ื”ืจ.
03:09
And what I learned very quickly
77
189139
2197
ื•ืžื” ืฉืœืžื“ืชื™ ืžื”ืจ ืžืื•ื“
03:11
is that we weren't doing a good job.
78
191336
3633
ื–ื” ืฉืื ื—ื ื• ืœื ืขื•ืฉื™ื ืขื‘ื•ื“ื” ื˜ื•ื‘ื”.
03:14
So I wanted to do things differently.
79
194969
2016
ืื– ืจืฆื™ืชื™ ืœืขืฉื•ืช ื“ื‘ืจื™ื ืื—ืจืช.
03:16
I wanted to introduce data and analytics
80
196985
2197
ืจืฆื™ืชื™ ืœื”ื›ื ื™ืก ื ืชื•ื ื™ื ื•ื ื™ืชื•ื—ื™ื ืกื˜ื˜ื™ืกื˜ื™ื™ื ืœืชื•ืš ื”ืขื‘ื•ื“ื” ืฉืœื ื•.
03:19
and rigorous statistical analysis
81
199182
2049
03:21
into our work.
82
201231
1400
03:22
In short, I wanted to moneyball criminal justice.
83
202631
2970
ื‘ืงื™ืฆื•ืจ, ืจืฆื™ืชื™ ืœื”ื›ื ื™ืก ืืช ื’ื™ืฉืช ื”ืžืื ื™ื‘ื•ืœ ืœืžืขืจื›ืช ื”ืžืฉืคื˜ ื”ืคืœื™ืœื™.
03:25
Now, moneyball, as many of you know,
84
205601
2027
ืžืื ื™ื‘ื•ืœ, ื›ืคื™ ืฉืจื‘ื™ื ืžื›ื ื™ื•ื“ืขื™ื,
03:27
is what the Oakland A's did,
85
207628
1569
ื–ื” ืžื” ืฉื”ืื•ืงืœื ื“ ืื™ื™'ื– ืขืฉื•,
03:29
where they used smart data and statistics
86
209197
1973
ื›ืฉื”ื ื”ืฉืชืžืฉื• ื‘ื ืชื•ื ื™ื ื•ืกื˜ื˜ื™ืกื˜ื™ืงื•ืช
03:31
to figure out how to pick players
87
211170
1622
ื›ื“ื™ ืœื”ื‘ื™ืŸ ืื™ืš ืœื‘ื—ื•ืจ ืฉื—ืงื ื™ื ืžื ืฆื—ื™ื,
03:32
that would help them win games,
88
212792
1521
03:34
and they went from a system that was based on baseball scouts
89
214313
2980
ื•ื”ื ืขื‘ืจื• ืžืฉื™ื˜ื” ืฉื”ืชื‘ืกืกื” ืขืœ ืฆื™ื™ื“ื™ ื›ืฉืจื•ื ื•ืช ื‘ื‘ื™ื™ืกื‘ื•ืœ
03:37
who used to go out and watch players
90
217293
1860
ืฉื”ืœื›ื• ื•ืฆืคื• ื‘ืฉื—ืงื ื™ื, ื•ื”ืฉืชืžืฉื• ื‘ื ื™ืกื™ื•ืŸ ื•ื‘ืื™ื ืกื˜ื™ืงื ื˜ื™ื ืฉืœื”ื --
03:39
and use their instinct and experience,
91
219153
1637
03:40
the scouts' instincts and experience,
92
220790
1743
ื ื™ืกื™ื•ืŸ ื•ืื™ื ืกื˜ื™ื ืงื˜ื™ื ืฉืœ ืฆื™ื™ื“ื™ ื›ืฉืจื•ื ื•ืช -- ื›ื“ื™ ืœื‘ื—ื•ืจ ืฉื—ืงื ื™ื,
03:42
to pick players, from one to use
93
222533
1713
ืœืฉื™ื˜ื” ื‘ื” ืžืฉืชืžืฉื™ื ื‘ื ืชื•ื ื™ื ื•ื ื™ืชื•ื—ื™ื ืงืคื“ื ื™ื™ื
03:44
smart data and rigorous statistical analysis
94
224246
2822
03:47
to figure out how to pick players that would help them win games.
95
227068
3371
ื›ื“ื™ ืœื”ื‘ื™ืŸ ืื™ืš ืœื‘ื—ื•ืจ ืฉื—ืงื ื™ื ืฉื™ืขื–ืจื• ืœื”ื ืœื ืฆื— ืžืฉื—ืงื™ื.
03:50
It worked for the Oakland A's,
96
230439
1798
ื–ื” ืขื‘ื“ ืœืื•ืงืœื ื“ ืื™ื™'ื–,
03:52
and it worked in the state of New Jersey.
97
232237
2219
ื•ื–ื” ืขื‘ื“ ื‘ืžื“ื™ื ืช ื ื™ื• ื’'ืจื–ื™.
03:54
We took Camden off the top of the list
98
234456
2073
ื”ืกืจื ื• ืืช ืงืžื“ืŸ ืžืจืืฉ ืจืฉื™ืžืช ื”ืขืจื™ื ื”ืžืกื•ื›ื ื•ืช ื‘ืืžืจื™ืงื”.
03:56
as the most dangerous city in America.
99
236529
2171
03:58
We reduced murders there by 41 percent,
100
238700
3155
ื”ืคื—ืชื ื• ืืช ืžืกืคืจ ื”ืจืฆื™ื—ื•ืช ืฉื ื‘-41 ืื—ื•ื–ื™ื,
04:01
which actually means 37 lives were saved.
101
241855
2982
ืžื” ืฉืื•ืžืจ ืฉื—ื™ื™ื”ื ืฉืœ 37 ื‘ื ื™ ืื“ื ื ื™ืฆืœื•.
04:04
And we reduced all crime in the city by 26 percent.
102
244837
3740
ื•ื”ืคื—ืชื ื• ืืช ื›ืœืœ ื”ืคืฉืข ื‘ืขื™ืจ ื‘-26 ืื—ื•ื–ื™ื.
04:08
We also changed the way we did criminal prosecutions.
103
248577
3239
ืฉื™ื ื™ื ื• ื’ื ืืช ืื•ืคืŸ ื”ื”ืขืžื“ื” ืœื“ื™ืŸ.
04:11
So we went from doing low-level drug crimes
104
251816
2005
ืื– ืขื‘ืจื ื• ืžื˜ื™ืคื•ืœ ื‘ืขื‘ื™ืจื•ืช ืกืžื™ื ืงืœื•ืช, ืฉื”ืชืจื—ืฉื• ืœื™ื“ ื”ื‘ื ื™ืŸ ืฉืœื ื•,
04:13
that were outside our building
105
253821
1642
04:15
to doing cases of statewide importance,
106
255463
2342
ืœื‘ื ื™ื™ืช ืชื™ืงื™ื ื‘ืขืœื™ ื—ืฉื™ื‘ื•ืช ืžื“ื™ื ื™ืช,
04:17
on things like reducing violence with the most violent offenders,
107
257805
3158
ื›ืžื• ืขืฆื™ืจืช ื”ืขื‘ืจื™ื™ื ื™ื ื”ื›ื™ ืืœื™ืžื™ื,
04:20
prosecuting street gangs,
108
260963
1858
ื”ืขืžื“ื” ืœื“ื™ืŸ ืฉืœ ื›ื ื•ืคื™ื•ืช ืจื—ื•ื‘,
04:22
gun and drug trafficking, and political corruption.
109
262821
3408
ืกื—ืจ ื‘ื ืฉืง ื•ืกืžื™ื, ื•ืฉื—ื™ืชื•ืช ืคื•ืœื™ื˜ื™ืช.
04:26
And all of this matters greatly,
110
266229
2502
ื•ื›ืœ ื–ื” ื—ืฉื•ื‘ ืžืื•ื“,
04:28
because public safety to me
111
268731
1945
ื›ื™, ืขื‘ื•ืจื™, ืฉืžื™ืจื” ืขืœ ื‘ื™ื˜ื—ื•ืŸ ื”ืฆื™ื‘ื•ืจ ื”ื•ื ื”ืชืคืงื™ื“ ื”ื—ืฉื•ื‘ ื‘ื™ื•ืชืจ ืฉืœ ื”ืžืžืฉืœ.
04:30
is the most important function of government.
112
270676
2536
04:33
If we're not safe, we can't be educated,
113
273212
2298
ื‘ืœื™ ื‘ื˜ื—ื•ืŸ - ืื™ืŸ ื—ื™ื ื•ืš,
04:35
we can't be healthy,
114
275510
1348
ืื™ืŸ ื‘ืจื™ืื•ืช,
04:36
we can't do any of the other things we want to do in our lives.
115
276858
2945
ืื™ ืืคืฉืจ ืœืขืฉื•ืช ืืช ืžื” ืฉืื ื—ื ื• ืจื•ืฆื™ื.
04:39
And we live in a country today
116
279803
1701
ื•ื‘ืžื“ื™ื ื” ืฉืœื ื• ื”ื™ื•ื,
04:41
where we face serious criminal justice problems.
117
281504
3134
ืื ื—ื ื• ืžืชืžื•ื“ื“ื™ื ืขื ื‘ืขื™ื•ืช ืจืฆื™ื ื™ื•ืช ื‘ืžืฉืคื˜ ืคืœื™ืœื™.
04:44
We have 12 million arrests every single year.
118
284638
3661
12 ืžื™ืœื™ื•ืŸ ืžืขืฆืจื™ื ืžืชื‘ืฆืขื™ื ืžื“ื™ ืฉื ื”.
04:48
The vast majority of those arrests
119
288299
2043
ืจื•ื‘ื ื”ืžื›ืจื™ืข ื”ื ืฉืœ ืขื‘ื™ืจื•ืช ืงืœื•ืช,
04:50
are for low-level crimes, like misdemeanors,
120
290342
3012
04:53
70 to 80 percent.
121
293354
1734
ื‘ื™ืŸ 70 ืœ-80 ืื—ื•ื–ื™ื.
04:55
Less than five percent of all arrests
122
295088
1991
ืคื—ื•ืช ืžื—ืžื™ืฉื” ืื—ื•ื–ื™ื ืฉืœ ื›ืœืœ ื”ืžืขืฆืจื™ื
04:57
are for violent crime.
123
297079
1895
ืงืฉื•ืจื™ื ืœืคืฉืขื™ื ืืœื™ืžื™ื.
04:58
Yet we spend 75 billion,
124
298974
2055
ื•ื‘ื›ืœ ื–ืืช ืื ื—ื ื• ืžืฉืงื™ืขื™ื 75 ืžื™ืœื™ืืจื“,
05:01
that's b for billion,
125
301029
1418
ื›ืŸ - ืžื™ืœื™ืืจื“,
05:02
dollars a year on state and local corrections costs.
126
302447
4127
ื“ื•ืœืจ ื›ืœ ืฉื ื” ืขืœ ื”ื•ืฆืื•ืช ืžื“ื™ื ื™ื•ืช ื•ืžืงื•ืžื™ื•ืช ืขืœ ืฉื™ืงื•ื ืืกื™ืจื™ื.
05:06
Right now, today, we have 2.3 million people
127
306574
2841
ื‘ืจื’ืข ื–ื”, ื”ื™ื•ื, ื™ืฉ ืœื ื• ื›-2.3 ืžื™ืœื™ื•ืŸ ืื ืฉื™ื
05:09
in our jails and prisons.
128
309415
1900
ื‘ื‘ืชื™ ื”ื›ืœื ื•ืกื•ื”ืจ ืฉืœื ื•.
05:11
And we face unbelievable public safety challenges
129
311315
2796
ื•ืื ื• ืขื•ืžื“ื™ื ื‘ืคื ื™ ืืชื’ืจื™ื ื‘ืœืชื™ ื™ืื•ืžื ื™ื ืœื‘ื™ื˜ื—ื•ืŸ ื”ืฆื™ื‘ื•ืจ
05:14
because we have a situation
130
314111
1939
ื›ื™ื•ื•ืŸ ืฉื™ืฉ ืœื ื• ืžืฆื‘ ื‘ื•
05:16
in which two thirds of the people in our jails
131
316050
2898
ืฉื ื™ ืฉืœื™ืฉ ืžื”ืื ืฉื™ื ื‘ื‘ืชื™ ื”ื›ืœื ืฉืœื ื•
05:18
are there waiting for trial.
132
318948
1754
ื ืžืฆืื™ื ืฉื ื‘ื”ืžืชื ื” ืœืžืฉืคื˜ ืฉืœื”ื.
05:20
They haven't yet been convicted of a crime.
133
320702
2135
ื”ื ืขื“ื™ื™ืŸ ืœื ื”ื•ืจืฉืขื• ื‘ื‘ื™ืฆื•ืข ืคืฉืข.
05:22
They're just waiting for their day in court.
134
322837
2119
ื”ื ืจืง ืžื—ื›ื™ื ืœื™ื•ื ืฉืœื”ื ื‘ื‘ื™ืช ื”ืžืฉืคื˜.
05:24
And 67 percent of people come back.
135
324956
3548
ื•-67 ืื—ื•ื–ื™ื ืžื”ืื ืฉื™ื ื—ื•ื–ืจื™ื.
05:28
Our recidivism rate is amongst the highest in the world.
136
328504
3028
ืฉื™ืขื•ืจ ื”ื—ื–ืจื” ืœื›ืœื ืฉืœื ื• ื”ื•ื ืžื”ื’ื‘ื•ื”ื™ื ื‘ืขื•ืœื.
05:31
Almost seven in 10 people who are released
137
331532
2103
ื›ืžืขื˜ ืฉื‘ืขื” ืžื›ืœ ืขืฉืจื” ืžืฉื•ื—ืจืจื™ื
05:33
from prison will be rearrested
138
333635
1651
ื™ื™ืขืฆืจื• ืžื—ื“ืฉ
05:35
in a constant cycle of crime and incarceration.
139
335286
3955
ื‘ืžื—ื–ื•ืจ ืงื‘ื•ืข ืฉืœ ืคืฉืข ื•ืžืืกืจ.
05:39
So when I started my job at the Arnold Foundation,
140
339241
2582
ื›ืš ืฉื›ืฉื”ืชื—ืœืชื™ ืืช ืขื‘ื•ื“ืชื™ ื‘ืงืจืŸ ืืจื ื•ืœื“,
05:41
I came back to looking at a lot of these questions,
141
341823
2736
ื”ืชื—ืœืชื™ ืฉื•ื‘ ืœื”ืกืชื›ืœ ืขืœ ืจื‘ื•ืช ืžื”ืฉืืœื•ืช ื”ืืœื•
05:44
and I came back to thinking about how
142
344559
1654
ื•ื”ืชื—ืœืชื™ ืฉื•ื‘ ืœื—ืฉื•ื‘ ืขืœ ืื™ืš ื”ืฉืชืžืฉื ื•
05:46
we had used data and analytics to transform
143
346213
2383
ื‘ืžื™ื“ืข ื•ื‘ื ื™ืชื•ื—ื™ื ืื ืœื™ื˜ื™ื™ื ื‘ื›ื“ื™ ืœืฉื ื•ืช
05:48
the way we did criminal justice in New Jersey.
144
348596
2584
ืืช ื”ื“ืจืš ื‘ื” ืื ื• ืขื•ืฉื™ื ืฆื“ืง ืžืฉืคื˜ื™ ื‘ื ื™ื•-ื’'ืจื–ื™.
05:51
And when I look at the criminal justice system
145
351180
2144
ื•ื›ืฉืื ื™ ืžืกืชื›ืœืช ืขืœ ืžืขืจื›ืช ื”ืžืฉืคื˜ ื”ืคืœื™ืœื™
05:53
in the United States today,
146
353324
1656
ื‘ืืจืฆื•ืช ื”ื‘ืจื™ืช ื›ื™ื•ื,
05:54
I feel the exact same way that I did
147
354980
1639
ืขื•ืœื” ื‘ื™ ื‘ื“ื™ื•ืง ืื•ืชื” ื”ืชื—ื•ืฉื”
05:56
about the state of New Jersey when I started there,
148
356619
2466
ืฉื”ื™ืชื” ืœื™ ืœื’ื‘ื™ ืžื“ื™ื ืช ื ื™ื•-ื’'ืจื–ื™ ื›ืฉื”ืชื—ืœืชื™ ืฉื,
05:59
which is that we absolutely have to do better,
149
359085
3228
ืฉื”ื™ื ืฉืื ื—ื ื• ืคืฉื•ื˜ ื—ื™ื™ื‘ื™ื ืœื”ืฉืชืคืจ,
06:02
and I know that we can do better.
150
362313
1923
ื•ืื ื™ ื™ื•ื“ืขืช ืฉืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื”ืฉืชืคืจ.
06:04
So I decided to focus
151
364236
1705
ืื– ื”ื—ืœื˜ืชื™ ืœื”ืชืžืงื“
06:05
on using data and analytics
152
365941
2217
ื‘ืฉื™ืžื•ืฉ ื‘ืžื™ื“ืข ื•ื ื™ืชื•ื—ื™ื ืื ืœื™ื˜ื™ื™ื
06:08
to help make the most critical decision
153
368158
2361
ื‘ื›ื“ื™ ืœืกื™ื™ืข ืœืงื‘ืœืช ื”ื”ื—ืœื˜ื” ื”ื—ืฉื•ื‘ื” ื‘ื™ื•ืชืจ
06:10
in public safety,
154
370519
1606
ื‘ื‘ื™ื˜ื—ื•ืŸ ืฆื™ื‘ื•ืจื™,
06:12
and that decision is the determination
155
372125
2021
ื•ื”ื”ื—ืœื˜ื” ื”ื–ื• ื”ื™ื ื”ืงื‘ื™ืขื”
06:14
of whether, when someone has been arrested,
156
374146
2535
ื”ืื, ื›ืืฉืจ ืžื™ืฉื”ื• ื ืขืฆืจ ืขืœ ื™ื“ื™ ื”ืžืฉื˜ืจื”,
06:16
whether they pose a risk to public safety
157
376681
1915
ื”ืื ื”ื ืžื”ื•ื•ื™ื ืกื›ื ื” ืœื‘ื™ื˜ื—ื•ืŸ ื”ืฆื™ื‘ื•ืจ
06:18
and should be detained,
158
378596
1526
ื•ืขืœื™ื”ื ืœื”ื™ื•ืช ืžืขื•ื›ื‘ื™ื,
06:20
or whether they don't pose a risk to public safety
159
380122
2356
ืื• ืฉื”ื ืื™ื ื ืžื”ื•ื•ื™ื ืกื›ื ื” ืœืฉืœื•ื ื”ืฆื™ื‘ื•ืจ
06:22
and should be released.
160
382478
1637
ื•ื™ืฉ ืœืฉื—ืจืจ ืื•ืชื.
06:24
Everything that happens in criminal cases
161
384115
1919
ื›ืœ ืžื” ืฉืงื•ืจื” ื‘ืžืฉืคื˜ื™ื ืคืœื™ืœื™ื™ื
06:26
comes out of this one decision.
162
386034
1772
ืžืงื•ืจื• ื‘ื”ื—ืœื˜ื” ื”ืื—ืช ื”ื–ื•.
06:27
It impacts everything.
163
387806
1496
ื”ื™ื ืžืฉืคื™ืขื” ืขืœ ื”ื›ืœ.
06:29
It impacts sentencing.
164
389302
1350
ื”ื™ื ืžืฉืคื™ืขื” ืขืœ ื’ื–ืจ ื”ื“ื™ืŸ.
06:30
It impacts whether someone gets drug treatment.
165
390652
1901
ื”ื™ื ืžืฉืคื™ืขื” ืขืœ ื”ืกื™ื›ื•ื™ ืฉืžื™ืฉื”ื• ื™ืงื‘ืœ ื˜ื™ืคื•ืœ ืœืกืžื™ื.
06:32
It impacts crime and violence.
166
392553
2323
ื”ื™ื ืžืฉืคื™ืขื” ืขืœ ืคืฉืข ื•ืขืœ ืืœื™ืžื•ืช.
06:34
And when I talk to judges around the United States,
167
394876
1937
ื•ื›ืฉืื ื™ ืžื“ื‘ืจืช ืขื ืฉื•ืคื˜ื™ื ื‘ืจื—ื‘ื™ ืืจื”"ื‘,
06:36
which I do all the time now,
168
396813
1928
ื“ื‘ืจ ืฉืื ื™ ืขื•ืฉื” ื›ืœ ื”ื–ืžืŸ ืขื›ืฉื™ื•,
06:38
they all say the same thing,
169
398741
1837
ื”ื ื›ื•ืœื ืื•ืžืจื™ื ืืช ืื•ืชื• ื”ื“ื‘ืจ,
06:40
which is that we put dangerous people in jail,
170
400578
3107
ื•ื”ื•ื ืฉืื ื• ืžื›ื ื™ืกื™ื ืื ืฉื™ื ืžืกื•ื›ื ื™ื ืœื‘ื™ืช ื”ืกื”ืจ,
06:43
and we let non-dangerous, nonviolent people out.
171
403685
3525
ื•ืื ื• ืžืฉื—ืจืจื™ื ืืช ื”ืื ืฉื™ื ื”ืœื-ืžืกื•ื›ื ื™ื ื•ื”ืœื-ืืœื™ืžื™ื.
06:47
They mean it and they believe it.
172
407210
2233
ื”ื ืžืชื›ื•ื•ื ื™ื ืœื–ื” ื•ืžืืžื™ื ื™ื ื‘ื–ื”.
06:49
But when you start to look at the data,
173
409443
1733
ืื‘ืœ ื›ืฉืžืชื—ื™ืœื™ื ืœื”ืกืชื›ืœ ืขืœ ื”ื ืชื•ื ื™ื,
06:51
which, by the way, the judges don't have,
174
411176
2464
ืฉืื•ืชื, ื“ืจืš ืื’ื‘, ื”ืฉื•ืคื˜ื™ื ืœื ืžื›ื™ืจื™ื,
06:53
when we start to look at the data,
175
413640
1612
ื•ื›ืฉืื ื—ื ื• ืžืชื—ื™ืœื™ื ืœื”ืกืชื›ืœ ืขืœ ื”ื ืชื•ื ื™ื,
06:55
what we find time and time again,
176
415252
2418
ืžื” ืฉืื ื• ืžื•ืฆืื™ื ืฉื•ื‘ ื•ืฉื•ื‘
06:57
is that this isn't the case.
177
417670
1982
ื”ื•ื ืฉื–ื” ืื™ื ื ื• ื›ืš.
06:59
We find low-risk offenders,
178
419652
1681
ืื ื—ื ื• ืžื•ืฆืื™ื ืคื•ืฉืขื™ื ืงื˜ื ื™ื ื•ืœื ืžืกื•ื›ื ื™ื,
07:01
which makes up 50 percent of our entire criminal justice population,
179
421333
3714
ืฉืžื”ื•ื•ื™ื 50 ืื—ื•ื– ืžื›ืœ ืื•ื›ืœื•ืกื™ื™ืช ืžืขืจื›ืช ื”ืžืฉืคื˜ ืฉืœื ื•,
07:05
we find that they're in jail.
180
425047
2399
ืื ื—ื ื• ืžื•ืฆืื™ื ืฉื”ื ื‘ื‘ื™ืช ื”ืกื”ืจ.
07:07
Take Leslie Chew, who was a Texas man
181
427446
2486
ืงื—ื• ืืช ืœืกืœื™ ืฆ'ื™ื•, ืื“ื ืžื˜ืงืกืก
07:09
who stole four blankets on a cold winter night.
182
429932
2884
ืฉื’ื ื‘ ืืจื‘ืข ืฉืžื™ื›ื•ืช ื‘ืœื™ืœื” ื—ื•ืจืคื™ ืงืจ.
07:12
He was arrested, and he was kept in jail
183
432816
2595
ื”ื•ื ื ืขืฆืจ, ื•ื”ื•ื ื ืฉืžืจ ื‘ื‘ื™ืช ื”ืกื”ืจ
07:15
on 3,500 dollars bail,
184
435411
2053
ืขืœ ืขืจื‘ื•ืช ืฉืœ 3,500 ื“ื•ืœืจ,
07:17
an amount that he could not afford to pay.
185
437464
2776
ืกื›ื•ื ืฉื”ื•ื ืœื ื™ื›ื•ืœ ื”ื™ื” ืœืฉืœื.
07:20
And he stayed in jail for eight months
186
440240
2588
ื•ื”ื•ื ื ืฉืืจ ื‘ื›ืœื ืฉืžื•ื ื” ื—ื•ื“ืฉื™ื
07:22
until his case came up for trial,
187
442828
2065
ืขื“ ืฉื”ืชื™ืง ืฉืœื• ืขืœื” ืœื‘ื™ืช ื”ืžืฉืคื˜,
07:24
at a cost to taxpayers of more than 9,000 dollars.
188
444893
3905
ื‘ืขืœื•ืช ืฉืœ ืžืขืœ 9,000 ื“ื•ืœืจ ืœืžืฉืœื ื”ืžื™ืกื™ื.
07:28
And at the other end of the spectrum,
189
448798
1997
ื•ื‘ืงืฆื” ื”ืฉื ื™ ืฉืœ ื”ืกืคืงื˜ืจื•ื,
07:30
we're doing an equally terrible job.
190
450795
2282
ืื ื—ื ื• ืขื•ืฉื™ื ืขื‘ื•ื“ื” ืจืขื” ืœื ืคื—ื•ืช.
07:33
The people who we find
191
453077
1572
ื”ืื ืฉื™ื ืฉืื ื• ื—ื•ืฉื‘ื™ื
07:34
are the highest-risk offenders,
192
454649
2019
ืœืคื•ืฉืขื™ื ื”ืžืกื•ื›ื ื™ื ื‘ื™ื•ืชืจ,
07:36
the people who we think have the highest likelihood
193
456668
2497
ื”ืื ืฉื™ื ืฉืื ื• ื—ื•ืฉื‘ื™ื ืฉืœื”ื ื™ืฉ ืืช ื”ืกื‘ื™ืจื•ืช ื”ื’ื‘ื•ื”ื” ื‘ื™ื•ืชืจ
07:39
of committing a new crime if they're released,
194
459165
1952
ืœื‘ืฆืข ืคืฉืข ื ื•ืกืฃ, ืื ื”ื ื™ืฉื•ื—ืจืจื•,
07:41
we see nationally that 50 percent of those people
195
461117
2950
ืื ื• ืจื•ืื™ื ื‘ืจืžื” ื”ืœืื•ืžื™ืช ืฉ-50 ืื—ื•ื– ืžื”ืื ืฉื™ื ื”ืืœื•
07:44
are being released.
196
464067
1974
ืžืฉื•ื—ืจืจื™ื.
07:46
The reason for this is the way we make decisions.
197
466041
3174
ื”ืกื™ื‘ื” ืœื›ืš ื”ื™ื ื”ื“ืจืš ื‘ื” ืื ื• ืžืงื‘ืœื™ื ื”ื—ืœื˜ื•ืช.
07:49
Judges have the best intentions
198
469215
1709
ืœืฉื•ืคื˜ื™ื ื™ืฉ ื›ื•ื•ื ื•ืช ื˜ื•ื‘ื•ืช
07:50
when they make these decisions about risk,
199
470924
1952
ื›ืฉื”ื ืžืงื‘ืœื™ื ืืช ื”ื”ื—ืœื˜ื•ืช ื”ืืœื• ืœื’ื‘ื™ ื”ืกื™ื›ื•ืŸ,
07:52
but they're making them subjectively.
200
472876
2484
ืื‘ืœ ื”ื ืžืงื‘ืœื™ื ืื•ืชืŸ ื‘ืื•ืคืŸ ืกื•ื‘ื™ื™ืงื˜ื™ื‘ื™.
07:55
They're like the baseball scouts 20 years ago
201
475360
2146
ื”ื ื›ืžื• ืฆื™ื™ื“ื™ ื”ื›ืฉืจื•ื ื•ืช ื‘ื‘ื™ื™ืกื‘ื•ืœ ืœืคื ื™ 20 ืฉื ื”
07:57
who were using their instinct and their experience
202
477506
2131
ืฉื”ืฉืชืžืฉื• ื‘ืื™ื ืกื˜ื™ื ืงื˜ื™ื ื•ื‘ื ื™ืกื™ื•ืŸ ืฉืœื”ื
07:59
to try to decide what risk someone poses.
203
479637
2679
ื›ื“ื™ ืœื ืกื•ืช ื•ืœื”ื—ืœื™ื˜ ื›ืžื” ืžืกื•ื›ืŸ ืžื™ืฉื”ื•.
08:02
They're being subjective,
204
482316
1530
ื”ื ืกื•ื‘ื™ื™ืงื˜ื™ื‘ื™ื™ื,
08:03
and we know what happens with subjective decision making,
205
483846
3060
ื•ืื ื• ื™ื•ื“ืขื™ื ืžื” ืงื•ืจื” ื›ืฉืžืงื‘ืœื™ื ื”ื—ืœื˜ื•ืช ื‘ืื•ืคืŸ ืกื•ื‘ื™ื™ืงื˜ื™ื‘ื™,
08:06
which is that we are often wrong.
206
486906
2743
ื•ื”ื•ื ืฉื”ืจื‘ื” ืคืขืžื™ื ืื ื—ื ื• ื˜ื•ืขื™ื.
08:09
What we need in this space
207
489649
1383
ืžื” ืฉืื ื—ื ื• ืฆืจื™ื›ื™ื ื‘ืžืจื—ื‘ ื”ื–ื”
08:11
are strong data and analytics.
208
491032
2552
ื”ื ื ืชื•ื ื™ื ืงืฉื™ื ื•ื ื™ืชื•ื—ื™ื.
08:13
What I decided to look for
209
493584
1747
ืžื” ืฉืื ื™ ื”ื—ืœื˜ืชื™ ืœื—ืคืฉ
08:15
was a strong data and analytic risk assessment tool,
210
495331
2836
ื”ื•ื ื›ืœื™ ืœื ื™ืชื•ื— ืกื™ื›ื•ื ื™ื ื•ื ืชื•ื ื™ื ืงืฉื™ื,
08:18
something that would let judges actually understand
211
498167
2764
ืžืฉื”ื• ืฉื™ืืคืฉืจ ืœืฉื•ืคื˜ื™ื ื‘ืืžืช ืœื”ื‘ื™ืŸ
08:20
with a scientific and objective way
212
500931
2259
ื‘ืื•ืคืŸ ืžื“ืขื™ ื•ืื•ื‘ื™ื™ืงื˜ื™ื‘ื™
08:23
what the risk was that was posed
213
503190
1647
ืžื” ื”ื™ื” ื”ืกื™ื›ื•ืŸ ืฉื ื‘ืข
08:24
by someone in front of them.
214
504837
1610
ืžืžื™ืฉื”ื• ืฉืขืžื“ ืœืคื ื™ื”ื.
08:26
I looked all over the country,
215
506447
1649
ื—ื™ืคืฉืชื™ ื‘ื›ืœ ื”ืžื“ื™ื ื”,
08:28
and I found that between five and 10 percent
216
508096
1942
ื•ืžืฆืืชื™ ืฉื‘ื™ืŸ ื—ืžื™ืฉื” ืœืขืฉืจื” ืื—ื•ื–ื™ื
08:30
of all U.S. jurisdictions
217
510038
1329
ืžื›ืœ ืžื—ื•ื–ื•ืช ื”ืฉื™ืคื•ื˜ ื”ืืžืจื™ืงืื™ื™ื
08:31
actually use any type of risk assessment tool,
218
511367
2978
ื‘ืขืฆื ืžืฉืชืžืฉื™ื ื‘ื›ืœื™ ื ื™ืชื•ื— ืกื™ื›ื•ื ื™ื ื›ืœืฉื”ื•
08:34
and when I looked at these tools,
219
514345
1625
ื•ื›ืฉื‘ื—ื ืชื™ ืืช ื”ื›ืœื™ื ื”ืœืœื• ืœืขื•ืžืง,
08:35
I quickly realized why.
220
515970
1860
ื”ื‘ื ืชื™ ืžื”ืจ ืžืื“ ืœืžื”.
08:37
They were unbelievably expensive to administer,
221
517830
2690
ื”ื ื”ื™ื• ื™ืงืจื™ื ืœืชื—ื–ื•ืง ื‘ืื•ืคืŸ ื‘ืœืชื™ ื ืชืคืฉ,
08:40
they were time-consuming,
222
520520
1528
ื”ื ื“ืจืฉื• ื–ืžืŸ ืจื‘,
08:42
they were limited to the local jurisdiction
223
522048
2107
ื•ื”ื ื”ื™ื• ืžื•ื’ื‘ืœื™ื ืœืžื—ื•ื– ื”ืฉื™ืคื•ื˜ื™ ื”ืžืงื•ืžื™
08:44
in which they'd been created.
224
524155
1430
ืฉื™ืฆืจ ืื•ืชื.
08:45
So basically, they couldn't be scaled
225
525585
1793
ื›ืš ืฉื‘ืขืฆื ืœื ื ื™ืชืŸ ื”ื™ื” ืœื”ื›ืœื™ืœ ืื•ืชื
08:47
or transferred to other places.
226
527378
2209
ืื• ืœื”ืขื‘ื™ืจ ืื•ืชื ืœืžืงื•ืžื•ืช ืื—ืจื™ื.
08:49
So I went out and built a phenomenal team
227
529587
2237
ืื– ื”ืœื›ืชื™ ื•ื‘ื ื™ืชื™ ืฆื•ื•ืช ืžื“ื”ื™ื
08:51
of data scientists and researchers
228
531824
2044
ืฉืœ ื—ื•ืงืจื™ื ื•ืžื“ืขื ื™ ืžื™ื“ืข
08:53
and statisticians
229
533868
1626
ื•ืฉืœ ืกื˜ื˜ื™ืกื˜ื™ืงืื™ื
08:55
to build a universal risk assessment tool,
230
535494
2845
ื‘ื›ื“ื™ ืœื‘ื ื•ืช ื›ืœื™ ืื•ื ื™ื‘ืจืกืœื™ ืœื”ืขืจื›ืช ืกื™ื›ื•ื ื™ื,
08:58
so that every single judge in the United States of America
231
538339
2393
ื›ืš ืฉื›ืœ ืฉื•ืคื˜ ื•ืฉื•ืคื˜ ื‘ืืจืฆื•ืช ื”ื‘ืจื™ืช
09:00
can have an objective, scientific measure of risk.
232
540732
4324
ื™ื•ื›ืœ ืœืงื‘ืœ ื”ืขืจื›ื” ืื•ื‘ื™ื™ืงื˜ื™ื‘ื™ืช ื•ืžื“ืขื™ืช ืฉืœ ืจืžืช ื”ืกื™ื›ื•ืŸ.
09:05
In the tool that we've built,
233
545056
1658
ื‘ื›ืœื™ ืฉื‘ื ื™ื ื•,
09:06
what we did was we collected 1.5 million cases
234
546714
2868
ืžื” ืฉืขืฉื™ื ื• ื”ื™ื” ืฉืืกืคื ื• 1.5 ืžื™ืœื™ื•ืŸ ืชื™ืงื™ื
09:09
from all around the United States,
235
549582
1698
ืžื›ืœ ืจื—ื‘ื™ ืืจื”"ื‘,
09:11
from cities, from counties,
236
551280
1644
ืžืขืจื™ื, ืžืžื—ื•ื–ื•ืช,
09:12
from every single state in the country,
237
552924
1511
ื•ืžื›ืœ ืžื“ื™ื ื” ื•ืžื“ื™ื ื” ื‘ืืจืฅ,
09:14
the federal districts.
238
554435
1746
ื•ืžื”ืžื—ื•ื–ื•ืช ื”ืคื“ืจืœื™ื™ื.
09:16
And with those 1.5 million cases,
239
556181
2189
ื•ืขื ืžื™ืœื™ื•ืŸ ื•ื—ืฆื™ ื”ืชื™ืงื™ื ื”ืืœื•,
09:18
which is the largest data set on pretrial
240
558370
1940
ืฉื”ื ืžืื’ืจ ื”ืžื™ื“ืข ื”ื’ื“ื•ืœ ื‘ื™ื•ืชืจ ืขืœ ื˜ืจื•ื-ืžืฉืคื˜
09:20
in the United States today,
241
560310
1805
ื‘ืืจื”"ื‘ ื›ื™ื•ื,
09:22
we were able to basically find that there were
242
562115
1865
ื”ืฆืœื—ื ื• ื‘ืขืฆื ืœืžืฆื•ื ืฉื”ื™ื•
09:23
900-plus risk factors that we could look at
243
563980
3322
ืžืขืœ ืœ-900 ื’ื•ืจืžื™ ืกื™ื›ื•ืŸ ืฉื™ื›ื•ืœื ื• ืœื‘ื—ื•ืŸ
09:27
to try to figure out what mattered most.
244
567302
2866
ืขืœ ืžื ืช ืœื ืกื•ืช ื•ืœื”ื‘ื™ืŸ ืžื” ื”ื™ื” ื”ื›ื™ ื—ืฉื•ื‘.
09:30
And we found that there were nine specific things
245
570168
2081
ื•ืžืฆืื ื• ืฉื”ื™ื• ืชืฉืขื” ื’ื•ืจืžื™ื ื™ื—ื•ื“ื™ื™ื
09:32
that mattered all across the country
246
572249
2235
ืฉื”ื™ื• ื—ืฉื•ื‘ื™ื ืœื›ืœ ืจื•ื—ื‘ ื”ืืจืฅ
09:34
and that were the most highly predictive of risk.
247
574484
2977
ื•ืฉื”ื™ื• ืžื ื‘ืื™ ื”ืกื™ื›ื•ืŸ ื”ื’ื‘ื•ื”ื™ื ื‘ื™ื•ืชืจ.
09:37
And so we built a universal risk assessment tool.
248
577461
3705
ื›ืš ืฉื‘ื ื™ื ื• ื›ืœื™ ืื•ื ื™ื‘ืจืกืœื™ ืœื”ืขืจื›ืช ืกื™ื›ื•ืŸ.
09:41
And it looks like this.
249
581166
1445
ื•ื”ื•ื ื ืจืื” ื›ืš.
09:42
As you'll see, we put some information in,
250
582611
2612
ื›ืคื™ ืฉืชื•ื›ืœื• ืœืจืื•ืช, ืื ื—ื ื• ืžื›ื ื™ืกื™ื ืžื™ื“ืข ืคื ื™ืžื”,
09:45
but most of it is incredibly simple,
251
585223
2013
ืื‘ืœ ื‘ืจื•ื‘ื• ื”ื•ื ืžืžืฉ ืคืฉื•ื˜,
09:47
it's easy to use,
252
587236
1432
ื”ื•ื ืคืฉื•ื˜ ืœืฉื™ืžื•ืฉ,
09:48
it focuses on things like the defendant's prior convictions,
253
588668
2969
ื”ื•ื ืžืชืžืงื“ ื‘ื“ื‘ืจื™ื ื›ื’ื•ืŸ ื”ื”ืจืฉืขื•ืช ื”ืงื•ื“ืžื•ืช ืฉืœ ื”ื ืืฉื,
09:51
whether they've been sentenced to incarceration,
254
591637
1979
ื”ืื ื”ื ื ืฉืคื˜ื• ืœืžืืกืจ,
09:53
whether they've engaged in violence before,
255
593616
2264
ื”ืื ื”ื ื”ื™ื• ืžืขื•ืจื‘ื™ื ื‘ืื™ืจื•ืขื™ื ืืœื™ืžื™ื ื‘ืขื‘ืจ,
09:55
whether they've even failed to come back to court.
256
595880
2393
ืืคื™ืœื• ืื ื”ื ืœื ื—ื–ืจื• ืœื‘ื™ืช ื”ืžืฉืคื˜ ื›ืฉื”ื™ื• ืฆืจื™ื›ื™ื.
09:58
And with this tool, we can predict three things.
257
598273
2500
ื•ืขื ื”ื›ืœื™ ื”ื–ื” ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื—ื–ื•ืช ืฉืœื•ืฉื” ื“ื‘ืจื™ื.
10:00
First, whether or not someone will commit
258
600773
1853
ื“ื‘ืจ ืจืืฉื•ืŸ, ื”ืื ืžื™ืฉื”ื• ื™ื‘ืฆืข ืื• ืœื
10:02
a new crime if they're released.
259
602626
1565
ืคืฉืข ื ื•ืกืฃ ืื ื”ื•ื ื™ืฉื•ื—ืจืจ.
10:04
Second, for the first time,
260
604191
1664
ื“ื‘ืจ ืฉื ื™, ื‘ืคืขื ื”ืจืืฉื•ื ื”,
10:05
and I think this is incredibly important,
261
605855
1861
ื•ืื ื™ ื—ื•ืฉื‘ืช ืฉื–ื” ื—ืฉื•ื‘ ืžืื“,
10:07
we can predict whether someone will commit
262
607716
1923
ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื ื‘ื ื”ืื ืžื™ืฉื”ื• ื™ื‘ืฆืข
10:09
an act of violence if they're released.
263
609639
1834
ืžืขืฉื” ืืœื™ื ืื ื”ื•ื ื™ืฉื•ื—ืจืจ.
10:11
And that's the single most important thing
264
611473
1887
ื•ื–ื” ื”ื“ื‘ืจ ื”ื—ืฉื•ื‘ ื‘ื™ื•ืชืจ
10:13
that judges say when you talk to them.
265
613360
1807
ืฉืฉื•ืคื˜ื™ื ืื•ืžืจื™ื ื›ืฉืžื“ื‘ืจื™ื ืืชื.
10:15
And third, we can predict whether someone
266
615167
1828
ื•ื“ื‘ืจ ืฉืœื™ืฉื™, ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื—ื–ื•ืช ืื ืžื™ืฉื”ื•
10:16
will come back to court.
267
616995
1990
ื™ื—ื–ื•ืจ ืœื‘ื™ืช ื”ืžืฉืคื˜.
10:18
And every single judge in the United States of America can use it,
268
618985
3033
ื•ื›ืœ ืฉื•ืคื˜ ื•ืฉื•ืคื˜ ื‘ืืจืฆื•ืช ื”ื‘ืจื™ืช ื™ื›ื•ืœ ืœื”ืฉืชืžืฉ ื‘ื–ื”,
10:22
because it's been created on a universal data set.
269
622018
3812
ื›ื™ื•ื•ืŸ ืฉื™ืฆืจื ื• ืืช ื–ื” ื‘ืžืื’ืจ ืžื™ื“ืข ืื•ื ื™ื‘ืจืกืœื™.
10:25
What judges see if they run the risk assessment tool
270
625830
2609
ืžื” ืฉืฉื•ืคื˜ื™ื ืจื•ืื™ื ืื ื”ื ืžืจื™ืฆื™ื ืืช ื›ืœื™ ื”ืขืจื›ืช ื”ืกื™ื›ื•ื ื™ื
10:28
is this -- it's a dashboard.
271
628439
2120
ื”ื•ื ื–ื” - ื–ื” ืœื•ื— ืžื—ื•ื•ื ื™ื.
10:30
At the top, you see the New Criminal Activity Score,
272
630559
2848
ื‘ืจืืฉ ืืชื ืจื•ืื™ื ืืช ืžื“ื“ ื”ืคืฉื™ืขื” ื”ื—ื“ืฉ,
10:33
six of course being the highest,
273
633407
1929
ื‘ื• ืฉืฉ ื”ื•ื ื”ืžื“ื“ ื”ื’ื‘ื•ื” ื‘ื™ื•ืชืจ,
10:35
and then in the middle you see, "Elevated risk of violence."
274
635336
2403
ื•ืื– ื‘ืžืจื›ื– ืืชื ืจื•ืื™ื "ืกื™ื›ื•ืŸ ืžื•ื’ื‘ืจ ืœืืœื™ืžื•ืช".
10:37
What that says is that this person
275
637739
1746
ืžื” ืฉื–ื” ืื•ืžืจ ื”ื•ื ืฉื”ืื“ื ื”ื–ื”
10:39
is someone who has an elevated risk of violence
276
639485
2060
ื”ื•ื ืื“ื ืฉืœื• ืกื™ื›ื•ืŸ ืžื•ื’ื‘ืจ ืœืืœื™ืžื•ืช
10:41
that the judge should look twice at.
277
641545
1885
ืฉืขืœ ื”ืฉื•ืคื˜ ืœื‘ื“ื•ืง ืœืขื•ืžืง.
10:43
And then, towards the bottom,
278
643430
1336
ื•ืื–, ืœืงืจืืช ื”ืชื—ืชื™ืช,
10:44
you see the Failure to Appear Score,
279
644766
1968
ืืชื ืจื•ืื™ื ืืช ืžื“ื“ ื”ื›ื™ืฉืœื•ืŸ ืœื”ื•ืคื™ืข,
10:46
which again is the likelihood
280
646734
1392
ืฉื”ื•ื ืฉื•ื‘ ื”ืกื™ื›ื•ื™
10:48
that someone will come back to court.
281
648126
3013
ืฉืžื™ืฉื”ื• ื™ื—ื–ื•ืจ ืœื‘ื™ืช ื”ืžืฉืคื˜.
10:51
Now I want to say something really important.
282
651139
2213
ืขื›ืฉื™ื• ืื ื™ ืจื•ืฆื” ืœื•ืžืจ ืžืฉื”ื• ืžืื“ ื—ืฉื•ื‘.
10:53
It's not that I think we should be eliminating
283
653352
2727
ื–ื” ืœื ืฉืื ื™ ื—ื•ืฉื‘ืช ืฉืขืœื™ื ื• ืœื”ื•ืฆื™ื
10:56
the judge's instinct and experience
284
656079
2244
ืืช ื”ืื™ื ืกื˜ื™ืงื˜ ื•ื”ื ื™ืกื™ื•ืŸ ืฉืœ ื”ืฉื•ืคื˜
10:58
from this process.
285
658323
1604
ืžื”ืชื”ืœื™ืš ื”ื–ื”.
10:59
I don't.
286
659927
1058
ืื ื™ ืœื.
11:00
I actually believe the problem that we see
287
660985
2007
ืœืžืขืฉื” ืื ื™ ืžืืžื™ื ื” ืฉื”ื‘ืขื™ื” ืฉืื ื—ื ื• ืจื•ืื™ื
11:02
and the reason that we have these incredible system errors,
288
662992
2854
ื•ื”ืกื™ื‘ื” ืฉื™ืฉ ืœื ื• ืืช ื˜ืขื•ื™ื•ืช ื”ืžืขืจื›ืช ื”ื‘ืœืชื™ ื ืชืคืกื•ืช ื”ืœืœื•,
11:05
where we're incarcerating low-level, nonviolent people
289
665846
3087
ื›ืฉืื ื—ื ื• ืขื•ืฆืจื™ื ืืช ื”ืื ืฉื™ื ื”ืœื-ืืœื™ืžื™ื, ื‘ืขืœื™ ื”ืกื™ื›ื•ืŸ ื”ื ืžื•ืš,
11:08
and we're releasing high-risk, dangerous people,
290
668933
3172
ื•ืื ื• ืžืฉื—ืจืจื™ื ืืช ื”ืื ืฉื™ื ื”ืžืกื•ื›ื ื™ื ื•ื‘ืจืžืช ื”ืกื™ื›ื•ืŸ ื”ื’ื‘ื•ื”ื”,
11:12
is that we don't have an objective measure of risk.
291
672105
2723
ื”ื™ื ืฉืื™ืŸ ืœื ื• ืžื“ื“ ืื•ื‘ื™ื™ืงื˜ื™ื‘ื™ ืฉืœ ืกื™ื›ื•ืŸ.
11:14
But what I believe should happen
292
674828
1300
ืื‘ืœ ืžื” ืฉืื ื™ ืžืืžื™ื ื” ืฉืฆืจื™ืš ืœืงืจื•ืช
11:16
is that we should take that data-driven risk assessment
293
676128
2800
ื–ื” ืฉืขืœื™ื ื• ืœืงื—ืช ืืช ื›ืœื™ ื”ืขืจื›ืช ื”ืกื™ื›ื•ื ื™ื ืžื‘ื•ืกืก ื”ื ืชื•ื ื™ื
11:18
and combine that with the judge's instinct and experience
294
678928
3041
ื•ืœืฉืœื‘ ืื•ืชื• ืขื ื”ืื™ื ืกื˜ื™ื ืงื˜ ื•ื”ื ื™ืกื™ื•ืŸ ืฉืœ ื”ืฉื•ืคื˜
11:21
to lead us to better decision making.
295
681969
2958
ื›ื“ื™ ืœื”ื•ื‘ื™ืœ ืื•ืชื ื• ืœืงื‘ืœืช ื”ื—ืœื˜ื•ืช ื˜ื•ื‘ื” ื™ื•ืชืจ.
11:24
The tool went statewide in Kentucky on July 1,
296
684927
3303
ื”ื›ืœื™ ื”ื•ื›ื ืก ืœืฉื™ืžื•ืฉ ื‘ื›ืœ ืžื“ื™ื ืช ืงื ื˜ืืงื™ ื‘ืจืืฉื•ืŸ ื‘ื™ื•ืœื™,
11:28
and we're about to go up in a number of other U.S. jurisdictions.
297
688230
3351
ื•ืื ื—ื ื• ืขื•ืžื“ื™ื ืœื”ืชื—ื™ืœ ื‘ืžืกืคืจ ืžื—ื•ื–ื•ืช ืฉื™ืคื•ื˜ ืืžืจื™ืงืื™ื™ื ืื—ืจื™ื.
11:31
Our goal, quite simply, is that every single judge
298
691581
2591
ืžื˜ืจืชื ื•, ืคืฉื•ื˜ ืžืื“, ื”ื™ื ืฉื›ืœ ืฉื•ืคื˜ ื•ืฉื•ืคื˜ ื‘ืืจื”"ื‘
11:34
in the United States will use a data-driven risk tool
299
694172
2192
ื™ืฉืชืžืฉ ื‘ื›ืœื™ ื”ืขืจื›ืช ืกื™ื›ื•ืŸ ืžื‘ื•ืกืก ื ืชื•ื ื™ื
11:36
within the next five years.
300
696364
2091
ื‘ืชื•ืš ื—ืžืฉ ื”ืฉื ื™ื ื”ืงืจื•ื‘ื•ืช.
11:38
We're now working on risk tools
301
698455
1352
ื›ืขืช ืื ื—ื ื• ืขื•ื‘ื“ื™ื ืขืœ ื›ืœื™ื ืœื”ืขืจื›ืช ืกื™ื›ื•ื ื™ื
11:39
for prosecutors and for police officers as well,
302
699807
3284
ื’ื ืขื‘ื•ืจ ืชื•ื‘ืขื™ื ื•ืฉื•ื˜ืจื™ื,
11:43
to try to take a system that runs today
303
703091
2700
ื‘ื›ื“ื™ ืœื ืกื•ืช ืœืงื—ืช ืžืขืจื›ืช ืฉืคื•ืขืœืช ื›ื™ื•ื ื‘ืืžืจื™ืงื”
11:45
in America the same way it did 50 years ago,
304
705791
2796
ื‘ืื•ืชื” ื”ื“ืจืš ื‘ื” ืคืขืœื” ืœืคื ื™ 50 ืฉื ื™ื,
11:48
based on instinct and experience,
305
708587
2097
ืชื•ืš ื”ืชื‘ืกืกื•ืช ืขืœ ืื™ื ืกื˜ื™ื ืงื˜ ื•ื ื™ืกื™ื•ืŸ,
11:50
and make it into one that runs
306
710684
1855
ื•ืœื”ืคื•ืš ืื•ืชื” ืœืื—ืช ืฉืคื•ืขืœืช
11:52
on data and analytics.
307
712539
2469
ืขืœ ื ืชื•ื ื™ื ื•ื ื™ืชื•ื—ื™ื.
11:55
Now, the great news about all this,
308
715008
1921
ืขื›ืฉื™ื•, ื”ื—ื“ืฉื•ืช ื”ื˜ื•ื‘ื•ืช ื‘ื›ืœ ื”ืขื ื™ื™ืŸ,
11:56
and we have a ton of work left to do,
309
716929
1617
ื•ื™ืฉ ืœื ื• ืขื•ื“ ื”ืžื•ืŸ ืขื‘ื•ื“ื” ืœืคื ื™ื ื•,
11:58
and we have a lot of culture to change,
310
718546
1857
ื•ื™ืฉ ืœื ื• ื”ืžื•ืŸ ืชืจื‘ื•ืช ืœืฉื ื•ืช,
12:00
but the great news about all of it
311
720403
1746
ืื‘ืœ ื”ื—ื“ืฉื•ืช ื”ืžืžืฉ ื˜ื•ื‘ื•ืช ื‘ื›ืœ ื”ืขื ื™ื™ืŸ
12:02
is that we know it works.
312
722149
1868
ื”ืŸ ืฉืื ื—ื ื• ื™ื•ื“ืขื™ื ืฉื–ื” ืขื•ื‘ื“.
12:04
It's why Google is Google,
313
724017
2153
ื–ื• ื”ืกื™ื‘ื” ืฉื’ื•ื’ืœ ื”ื™ื ื’ื•ื’ืœ,
12:06
and it's why all these baseball teams use moneyball
314
726170
2462
ื•ื–ื• ื”ืกื™ื‘ื” ืฉื›ืœ ืื•ืชืŸ ืงื‘ื•ืฆื•ืช ื”ื‘ื™ื™ืกื‘ื•ืœ ืžืฉืชืžืฉื•ืช ื‘ืžืื ื™ื‘ื•ืœ
12:08
to win games.
315
728632
1781
ื‘ื›ื“ื™ ืœื ืฆื— ืžืฉื—ืงื™ื.
12:10
The great news for us as well
316
730413
1737
ื”ื—ื“ืฉื•ืช ื”ื˜ื•ื‘ื•ืช ืขื‘ื•ืจื ื• ื’ื
12:12
is that it's the way that we can transform
317
732150
1896
ื”ืŸ ืฉืื—ื ื• ื™ื›ื•ืœื™ื ืœืฉื ื•ืช ืืช
12:14
the American criminal justice system.
318
734046
2321
ืžืขืจื›ืช ื”ืžืฉืคื˜ ื”ืคืœื™ืœื™ืช ื”ืืžืจื™ืงืื™ืช.
12:16
It's how we can make our streets safer,
319
736367
2357
ื–ื• ื”ื“ืจืš ื‘ื” ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื”ืคื•ืš ืืช ื”ืจื—ื•ื‘ื•ืช ืฉืœื ื• ืœื‘ื˜ื•ื—ื™ื ื™ื•ืชืจ,
12:18
we can reduce our prison costs,
320
738724
2299
ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœืฆืžืฆื ืืช ื”ื•ืฆืื•ืช ื‘ืชื™ ื”ื›ืœื ืฉืœื ื•,
12:21
and we can make our system much fairer
321
741023
2067
ื•ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื”ืคื•ืš ืืช ื”ืžืขืจื›ืช ืฉืœื ื• ืœื”ื•ื’ื ืช ื”ืจื‘ื” ื™ื•ืชืจ
12:23
and more just.
322
743090
1725
ื•ื™ื•ืชืจ ืฆื•ื“ืงืช.
12:24
Some people call it data science.
323
744815
2162
ื™ืฉื ื ืื ืฉื™ื ื”ืงื•ืจืื™ื ืœื–ื” ืžื“ืข ื ืชื•ื ื™ื.
12:26
I call it moneyballing criminal justice.
324
746977
2301
ืื ื™ ืงื•ืจืืช ืœื–ื” ืœืขืฉื•ืช ืžืื ื™ื‘ื•ืœื™ื ื’ ืœืฉื™ืคื•ื˜ ื”ืคืœื™ืœื™.
12:29
Thank you.
325
749278
1804
ืชื•ื“ื” ืจื‘ื”.
12:31
(Applause)
326
751082
4093
(ืชืฉื•ืื•ืช)
ืขืœ ืืชืจ ื–ื”

ืืชืจ ื–ื” ื™ืฆื™ื’ ื‘ืคื ื™ื›ื ืกืจื˜ื•ื ื™ YouTube ื”ืžื•ืขื™ืœื™ื ืœืœื™ืžื•ื“ ืื ื’ืœื™ืช. ืชื•ื›ืœื• ืœืจืื•ืช ืฉื™ืขื•ืจื™ ืื ื’ืœื™ืช ื”ืžื•ืขื‘ืจื™ื ืขืœ ื™ื“ื™ ืžื•ืจื™ื ืžื”ืฉื•ืจื” ื”ืจืืฉื•ื ื” ืžืจื—ื‘ื™ ื”ืขื•ืœื. ืœื—ืฅ ืคืขืžื™ื™ื ืขืœ ื”ื›ืชื•ื‘ื™ื•ืช ื‘ืื ื’ืœื™ืช ื”ืžื•ืฆื’ื•ืช ื‘ื›ืœ ื“ืฃ ื•ื™ื“ืื• ื›ื“ื™ ืœื”ืคืขื™ืœ ืืช ื”ืกืจื˜ื•ืŸ ืžืฉื. ื”ื›ืชื•ื‘ื™ื•ืช ื’ื•ืœืœื•ืช ื‘ืกื ื›ืจื•ืŸ ืขื ื”ืคืขืœืช ื”ื•ื•ื™ื“ืื•. ืื ื™ืฉ ืœืš ื”ืขืจื•ืช ืื• ื‘ืงืฉื•ืช, ืื ื ืฆื•ืจ ืื™ืชื ื• ืงืฉืจ ื‘ืืžืฆืขื•ืช ื˜ื•ืคืก ื™ืฆื™ืจืช ืงืฉืจ ื–ื”.

https://forms.gle/WvT1wiN1qDtmnspy7