TED2015
Rajiv Maheswaran: The math behind basketball's wildest moves
Radživ Mahesvaran (Rajiv Maheswaran): Matematika iza najluđih pokreta u košarci
Filmed:
Readability: 3.1
2,683,104 views
Košarka je brza igra sa improvizacijom, kontaktom i, khm, spacio-temporalnom šemom rekognicije. Radživ Mahesvaran i njegove kolege analiziraju pokrete iza ključnih delova utakmice, kako bi pomogli trenerima i igračima da kombinuju intuiciju sa novim podacima. Bonus: Ono što oni izučavaju bi moglo da nam pomogne da razumemo kako se ljudi kreću svuda.
Rajiv Maheswaran - Researcher
Using advanced data analysis tools, Rajiv Maheswaran and Second Spectrum help make basketball teams smarter. Full bio
Using advanced data analysis tools, Rajiv Maheswaran and Second Spectrum help make basketball teams smarter. Full bio
Double-click the English transcript below to play the video.
Moje kolege i mene fascinira
nauka o pokretnim tačkama.
nauka o pokretnim tačkama.
00:12
My colleagues and I are fascinated
by the science of moving dots.
by the science of moving dots.
0
954
3583
00:16
So what are these dots?
1
4927
1150
Kakve su to tačke?
00:18
Well, it's all of us.
2
6101
1287
Pa, to smo svi mi.
00:19
And we're moving in our homes,
in our offices, as we shop and travel
in our offices, as we shop and travel
3
7412
5085
Krećemo se u našim domovima
i kancelarijama
i kancelarijama
dok kupujemo i putujemo
po gradovima i svetu.
po gradovima i svetu.
00:24
throughout our cities
and around the world.
and around the world.
4
12521
2066
00:26
And wouldn't it be great
if we could understand all this movement?
if we could understand all this movement?
5
14958
3669
Zar ne bi bilo sjajno da možemo
da razumemo sve ove pokrete?
da razumemo sve ove pokrete?
00:30
If we could find patterns and meaning
and insight in it.
and insight in it.
6
18918
2890
Da imamo uvid u njihove šeme i značenja.
00:34
And luckily for us, we live in a time
7
22259
1785
A srećom po nas, živimo u vremenu
00:36
where we're incredibly good
at capturing information about ourselves.
at capturing information about ourselves.
8
24068
4497
u kom nam neverovatno dobro ide
da pratimo informacije o sebi.
da pratimo informacije o sebi.
00:40
So whether it's through
sensors or videos, or apps,
sensors or videos, or apps,
9
28807
3663
Bilo da je to putem senzora,
snimaka ili aplikacija,
snimaka ili aplikacija,
00:44
we can track our movement
with incredibly fine detail.
with incredibly fine detail.
10
32494
2809
možemo vrlo detaljno pratiti naše pokrete.
00:48
So it turns out one of the places
where we have the best data about movement
where we have the best data about movement
11
36092
5032
Ispada da je jedno od mesta
gde imamo najviše podataka o pokretu
gde imamo najviše podataka o pokretu
00:53
is sports.
12
41148
1208
sport.
00:54
So whether it's basketball or baseball,
or football or the other football,
or football or the other football,
13
42682
5333
Bilo da je to košarka, bejzbol,
ili američki fudbal ili onaj drugi fudbal,
ili američki fudbal ili onaj drugi fudbal,
01:00
we're instrumenting our stadiums
and our players to track their movements
and our players to track their movements
14
48039
4402
postavljamo instrumente na stadione
i igrače da bismo pratili njihovo kretanje
i igrače da bismo pratili njihovo kretanje
u svakom deliću sekunde.
01:04
every fraction of a second.
15
52465
1313
01:05
So what we're doing
is turning our athletes into --
is turning our athletes into --
16
53802
4382
Ono što radimo je da pretvaramo
naše sportiste u -
naše sportiste u -
01:10
you probably guessed it --
17
58208
1959
verovatno već pretpostavljate -
01:12
moving dots.
18
60191
1396
pokretne tačke.
01:13
So we've got mountains of moving dots
and like most raw data,
and like most raw data,
19
61946
4934
Tako imamo gomilu pokretnih tački,
i slično većini neobrađenih podataka,
i slično većini neobrađenih podataka,
01:18
it's hard to deal with
and not that interesting.
and not that interesting.
20
66904
2502
teško je raditi sa njima,
a nije baš ni zanimljivo.
a nije baš ni zanimljivo.
01:21
But there are things that, for example,
basketball coaches want to know.
basketball coaches want to know.
21
69430
3769
Ali postoje stvari koje, na primer,
košarkaški treneri žele da znaju.
košarkaški treneri žele da znaju.
01:25
And the problem is they can't know them
because they'd have to watch every second
because they'd have to watch every second
22
73223
3810
A problem je što ne mogu da ih znaju
zato što bi morali da gledaju svaki sekund
zato što bi morali da gledaju svaki sekund
01:29
of every game, remember it and process it.
23
77057
2589
svake utakmice, sve to zapamte i obrade.
01:31
And a person can't do that,
24
79804
1930
A čovek to ne može,
01:33
but a machine can.
25
81758
1310
ali mašina može.
01:35
The problem is a machine can't see
the game with the eye of a coach.
the game with the eye of a coach.
26
83661
3410
Problem je što mašina
ne vidi utakmicu očima trenera.
ne vidi utakmicu očima trenera.
01:39
At least they couldn't until now.
27
87363
2261
Bar do sada nije mogla.
01:42
So what have we taught the machine to see?
28
90228
2103
Šta smo to naučili mašinu da vidi?
01:45
So, we started simply.
29
93569
1787
Pa, počeli smo sa osnovama.
01:47
We taught it things like passes,
shots and rebounds.
shots and rebounds.
30
95380
3799
Naučili smo je stvarima kao što su pasovi,
šutevi i skok pod košem.
šutevi i skok pod košem.
01:51
Things that most casual fans would know.
31
99203
2541
Stvarima koje zna
većina prosečnih obožavalaca.
većina prosečnih obožavalaca.
01:53
And then we moved on to things
slightly more complicated.
slightly more complicated.
32
101768
2832
A potom smo prešli
na malo komplikovanije stvari.
na malo komplikovanije stvari.
01:56
Events like post-ups,
and pick-and-rolls, and isolations.
and pick-and-rolls, and isolations.
33
104624
4588
Događaje poput postapova,
pik end rola i presinga.
pik end rola i presinga.
02:01
And if you don't know them, that's okay.
Most casual players probably do.
Most casual players probably do.
34
109377
3543
Ako ne znate te pojmove, u redu je.
Većina prosečnih igrača zna.
Većina prosečnih igrača zna.
02:05
Now, we've gotten to a point where today,
the machine understands complex events
the machine understands complex events
35
113560
5340
E, sad, došli smo do tačke da danas
mašina razume kompleksne događaje
mašina razume kompleksne događaje
02:10
like down screens and wide pins.
36
118924
3073
poput akcija i vajd pinova.
02:14
Basically things only professionals know.
37
122021
2726
Praktično, ono što znaju
samo profesionalci.
samo profesionalci.
02:16
So we have taught a machine to see
with the eyes of a coach.
with the eyes of a coach.
38
124771
4388
Zapravo, naučili smo mašinu
da vidi očima trenera.
da vidi očima trenera.
02:22
So how have we been able to do this?
39
130009
1857
Kako smo ovo uspeli?
02:24
If I asked a coach to describe
something like a pick-and-roll,
something like a pick-and-roll,
40
132511
3118
Ako pitam trenera da opiše
nešto poput pik end rola,
nešto poput pik end rola,
02:27
they would give me a description,
41
135653
1640
on mi objasni šta je to,
i ako bih to ubacio u algoritam,
izgledalo bi užasno.
izgledalo bi užasno.
02:29
and if I encoded that as an algorithm,
it would be terrible.
it would be terrible.
42
137317
2856
02:33
The pick-and-roll happens to be this dance
in basketball between four players,
in basketball between four players,
43
141026
4278
Stvar je u tome što je pik end rol
u košarci ples između četiri igrača,
u košarci ples između četiri igrača,
02:37
two on offense and two on defense.
44
145328
1912
dva u napadu i dva u odbrani.
02:39
And here's kind of how it goes.
45
147486
1618
I evo kako to otprilike ide.
02:41
So there's the guy on offense
without the ball
without the ball
46
149128
2533
Jedan momak je u napadu bez lopte
02:43
the ball and he goes next to the guy
guarding the guy with the ball,
guarding the guy with the ball,
47
151685
3209
i on ide do momka
koji čuva drugog momka sa loptom
koji čuva drugog momka sa loptom
i otprilike ostaje tamo,
02:46
and he kind of stays there
48
154918
1257
obojica se pomeraju i nešto se dešava,
i ta-da, to je pik end rol.
i ta-da, to je pik end rol.
02:48
and they both move and stuff happens,
and ta-da, it's a pick-and-roll.
and ta-da, it's a pick-and-roll.
49
156199
3317
02:51
(Laughter)
50
159540
2215
(Smeh)
02:53
So that is also an example
of a terrible algorithm.
of a terrible algorithm.
51
161779
2508
To je takođe, jedan primer
užasnog algoritma.
užasnog algoritma.
02:56
So, if the player who's the interferer --
he's called the screener --
he's called the screener --
52
164913
4204
Tako, ako igrač koji vrši udvajanje -
on se zove bloker -
on se zove bloker -
03:01
goes close by, but he doesn't stop,
53
169278
2872
prilazi blizu, ali se ne zaustavlja,
03:04
it's probably not a pick-and-roll.
54
172174
1765
to verovatno nije pik end rol.
03:06
Or if he does stop,
but he doesn't stop close enough,
but he doesn't stop close enough,
55
174560
3945
Ili ako se zaustavi,
ali se ne zaustavi dovoljno blizu,
ali se ne zaustavi dovoljno blizu,
03:10
it's probably not a pick-and-roll.
56
178529
1761
to verovatno opet nije pik end rol.
03:12
Or, if he does go close by
and he does stop
and he does stop
57
180642
3237
Ili, ako priđe blizu i zaustavi se,
03:15
but they do it under the basket,
it's probably not a pick-and-roll.
it's probably not a pick-and-roll.
58
183903
3324
ali to uradi pod košem,
to verovatno nije pik end rol.
to verovatno nije pik end rol.
03:19
Or I could be wrong,
they could all be pick-and-rolls.
they could all be pick-and-rolls.
59
187462
2524
Ili ja možda grešim, možda je
sve to pik end rol.
sve to pik end rol.
03:22
It really depends on the exact timing,
the distances, the locations,
the distances, the locations,
60
190010
4568
To zaista zavisi od preciznog tajminga,
udaljenosti, lokacije,
udaljenosti, lokacije,
03:26
and that's what makes it hard.
61
194602
1495
i to je ono što otežava stvari.
03:28
So, luckily, with machine learning,
we can go beyond our own ability
we can go beyond our own ability
62
196579
4944
Srećom, sa mašinskim učenjem,
možemo da idemo dalje od naše sposobnosti
možemo da idemo dalje od naše sposobnosti
03:33
to describe the things we know.
63
201547
1743
da opišemo stvari koje znamo.
03:35
So how does this work?
Well, it's by example.
Well, it's by example.
64
203314
2280
Kako ovo funkcioniše? Pa, po primeru.
03:37
So we go to the machine and say,
"Good morning, machine.
"Good morning, machine.
65
205759
2830
Odemo do mašine i kažemo,
"Dobro jutro, mašino.
"Dobro jutro, mašino.
03:41
Here are some pick-and-rolls,
and here are some things that are not.
and here are some things that are not.
66
209077
3359
Evo nekih pik end rolova,
evo nekih stvari koje nisu.
evo nekih stvari koje nisu.
03:44
Please find a way to tell the difference."
67
212720
2252
Molim te, nađi način da napraviš razliku."
03:47
And the key to all of this is to find
features that enable it to separate.
features that enable it to separate.
68
215076
3707
I ključ za sve ovo je pronaći svojstva
koja joj omogućavaju da to raščlani.
koja joj omogućavaju da to raščlani.
03:50
So if I was going
to teach it the difference
to teach it the difference
69
218807
2109
Tako, ako bih hteo da je naučim razlici
03:52
between an apple and orange,
70
220940
1381
između jabuke i pomorandže,
03:54
I might say, "Why don't you
use color or shape?"
use color or shape?"
71
222345
2375
mogao bih da kažem:
"Što ne uzmeš boju ili obllk?"
"Što ne uzmeš boju ili obllk?"
03:56
And the problem that we're solving is,
what are those things?
what are those things?
72
224744
2943
Problem koji rešavamo je,
šta su to te stvari?
šta su to te stvari?
03:59
What are the key features
73
227711
1247
Koje su ključne stavke
04:00
that let a computer navigate
the world of moving dots?
the world of moving dots?
74
228982
3499
koje kompjuteru omogućavaju da
upravlja svetom pokretnih tački?
upravlja svetom pokretnih tački?
04:04
So figuring out all these relationships
with relative and absolute location,
with relative and absolute location,
75
232505
4823
Razumevši sve ove veze
sa relativnom i apsolutnom lokacijom,
sa relativnom i apsolutnom lokacijom,
04:09
distance, timing, velocities --
76
237352
1909
udaljenost, tajming, brzina -
04:11
that's really the key to the science
of moving dots, or as we like to call it,
of moving dots, or as we like to call it,
77
239440
4928
to je zaista ključ nauke o pokretnim
tačkama ili kako mi volimo da zovemo,
tačkama ili kako mi volimo da zovemo,
04:16
spatiotemporal pattern recognition,
in academic vernacular.
in academic vernacular.
78
244392
3344
spaciotemporalna šema prepoznavanja,
akademskim žargonom govoreći.
akademskim žargonom govoreći.
04:19
Because the first thing is,
you have to make it sound hard --
you have to make it sound hard --
79
247925
2898
Jer kao prvo, mora da zvuči teško -
04:22
because it is.
80
250847
1278
jer to i jeste.
04:24
The key thing is, for NBA coaches,
it's not that they want to know
it's not that they want to know
81
252410
3141
Ključna stvar, za NBA trenere,
nije to da žele da znaju
nije to da žele da znaju
04:27
whether a pick-and-roll happened or not.
82
255575
1922
da li je došlo do pik end rola ili ne.
04:29
It's that they want to know
how it happened.
how it happened.
83
257521
2076
Oni žele da znaju kako se odvijao.
04:31
And why is it so important to them?
So here's a little insight.
So here's a little insight.
84
259621
2986
A zašto je to njima tako važno?
Evo malog uvida.
Evo malog uvida.
04:34
It turns out in modern basketball,
85
262631
1771
Izgleda da je u modernoj košarci
04:36
this pick-and-roll is perhaps
the most important play.
the most important play.
86
264426
2539
ovaj pik end rol možda
najvažniji deo igre.
najvažniji deo igre.
04:39
And knowing how to run it,
and knowing how to defend it,
and knowing how to defend it,
87
267065
2620
Znati kako treba da se izvede,
i kako da se odbrani,
i kako da se odbrani,
04:41
is basically a key to winning
and losing most games.
and losing most games.
88
269709
2670
je suštinski ključ pobede
ili poraza u većini utakmica.
ili poraza u većini utakmica.
04:44
So it turns out that this dance
has a great many variations
has a great many variations
89
272403
3801
Tako ispada da ovaj ples
ima mnoge varijacije
ima mnoge varijacije
04:48
and identifying the variations
is really the thing that matters,
is really the thing that matters,
90
276228
3648
i identifikovanje tih varijacija
je ono što je stvarno važno,
je ono što je stvarno važno,
04:51
and that's why we need this
to be really, really good.
to be really, really good.
91
279900
2529
i zato nam je potrebno da ovo
bude baš, baš dobro.
bude baš, baš dobro.
04:55
So, here's an example.
92
283228
1176
Evo jednog primera.
04:56
There are two offensive
and two defensive players,
and two defensive players,
93
284428
2379
Imamo dva igrača u napadu
i dva igrača u odbrani,
i dva igrača u odbrani,
04:58
getting ready to do
the pick-and-roll dance.
the pick-and-roll dance.
94
286831
2152
spremni su da izvedu pik end rol ples.
05:01
So the guy with ball
can either take, or he can reject.
can either take, or he can reject.
95
289007
2683
Igrač sa loptom može
ili prihvatiti, ili odbiti.
ili prihvatiti, ili odbiti.
05:04
His teammate can either roll or pop.
96
292086
3001
Saigrač se može ili saviti ili otvoriti.
05:07
The guy guarding the ball
can either go over or under.
can either go over or under.
97
295111
2986
Momak koji čuva loptu
može ići iznad ili ispod.
može ići iznad ili ispod.
05:10
His teammate can either show
or play up to touch, or play soft
or play up to touch, or play soft
98
298121
4565
Njegov saigrač može ili da se otkrije
ili da igra do kontakta, ili bez kontakta
ili da igra do kontakta, ili bez kontakta
05:14
and together they can
either switch or blitz
either switch or blitz
99
302710
2618
i zajedno mogu ili
da se zamene ili napadnu
da se zamene ili napadnu
05:17
and I didn't know
most of these things when I started
most of these things when I started
100
305352
2659
a nisam znao većinu ovih
stvari kada sam počinjao
stvari kada sam počinjao
05:20
and it would be lovely if everybody moved
according to those arrows.
according to those arrows.
101
308035
3920
i bilo bi divno kada bi se svi pomerali
u skladu sa ovim strelicama.
u skladu sa ovim strelicama.
05:23
It would make our lives a lot easier,
but it turns out movement is very messy.
but it turns out movement is very messy.
102
311979
3905
To bi umnogome olakšalo naše živote,
ali izgleda da su naši pokreti zbrkani.
ali izgleda da su naši pokreti zbrkani.
05:28
People wiggle a lot and getting
these variations identified
these variations identified
103
316047
5484
Ljudi se mnogo meškolje i dobijanje
ovih identifikovanih varijacija
ovih identifikovanih varijacija
05:33
with very high accuracy,
104
321555
1303
sa veoma velikom tačnošću,
05:34
both in precision and recall, is tough
105
322882
1868
i u preciznosti i povlačenju, je teško
05:36
because that's what it takes to get
a professional coach to believe in you.
a professional coach to believe in you.
106
324774
3618
jer zbog toga je potrebno da imaš
profesionalnog trenera koji veruje u tebe.
profesionalnog trenera koji veruje u tebe.
05:40
And despite all the difficulties
with the right spatiotemporal features
with the right spatiotemporal features
107
328416
3380
I uprkos svim poteškoćama sa tačnim
spaciotemporalnim karakteristikama,
spaciotemporalnim karakteristikama,
05:43
we have been able to do that.
108
331820
1474
mi smo to uradili.
05:45
Coaches trust our ability of our machine
to identify these variations.
to identify these variations.
109
333318
3927
Treneri veruju mogućnostima naših mašina
da identifikuju ove varijacije.
da identifikuju ove varijacije.
05:49
We're at the point where
almost every single contender
almost every single contender
110
337478
3533
Došli smo do tačke gde
skoro svaki kandidat
skoro svaki kandidat
05:53
for an NBA championship this year
111
341035
1623
za NBA šampionat ove godine
05:54
is using our software, which is built
on a machine that understands
on a machine that understands
112
342682
4408
koristi naš softver, koji je ugrađen
u mašinu koja razume
u mašinu koja razume
05:59
the moving dots of basketball.
113
347114
1634
pokretne tačke u košarci.
06:01
So not only that, we have given advice
that has changed strategies
that has changed strategies
114
349872
5153
I ne samo to, davali smo savete
koji menjaju strategije
koji menjaju strategije
06:07
that have helped teams win
very important games,
very important games,
115
355049
3352
koje pomažu timovima
da dobiju veoma važne utakmice,
da dobiju veoma važne utakmice,
06:10
and it's very exciting because you have
coaches who've been in the league
coaches who've been in the league
116
358425
3732
a to je vrlo uzbudljivo jer imate
trenere koji su u ligi
trenere koji su u ligi
06:14
for 30 years that are willing to take
advice from a machine.
advice from a machine.
117
362181
3067
i po 30 godina i koji su spremni da
prihvate savet od mašine.
prihvate savet od mašine.
06:17
And it's very exciting,
it's much more than the pick-and-roll.
it's much more than the pick-and-roll.
118
365874
2906
I to je vrlo uzbudljivo,
to je mnogo više od pik end rola.
to je mnogo više od pik end rola.
06:20
Our computer started out
with simple things
with simple things
119
368804
2076
Naš kompjuter je počeo sa prostim stvarima
06:22
and learned more and more complex things
120
370904
2064
i učio sve komplikovanije stvari
06:24
and now it knows so many things.
121
372992
1561
tako da sada zna dosta toga.
06:26
Frankly, I don't understand
much of what it does,
much of what it does,
122
374577
2835
Iskreno, ni ja ne razumem
dosta toga što on radi,
dosta toga što on radi,
06:29
and while it's not that special
to be smarter than me,
to be smarter than me,
123
377436
3715
i dok nije toliko teško biti
pametniji od mene,
pametniji od mene,
06:33
we were wondering,
can a machine know more than a coach?
can a machine know more than a coach?
124
381175
3644
pitali smo se, može li neka
mašina da zna više od trenera?
mašina da zna više od trenera?
06:36
Can it know more than person could know?
125
384843
2055
Može li da zna više od nego čovek?
06:38
And it turns out the answer is yes.
126
386922
1745
I izgleda da je odgovor da.
06:40
The coaches want players
to take good shots.
to take good shots.
127
388691
2557
Treneri žele da im igrači imaju dobar šut.
06:43
So if I'm standing near the basket
128
391272
1651
Ako ja stojim blizu koša
06:44
and there's nobody near me,
it's a good shot.
it's a good shot.
129
392947
2166
i nema nikoga u blizini,
to je dobra pozicija.
to je dobra pozicija.
06:47
If I'm standing far away surrounded
by defenders, that's generally a bad shot.
by defenders, that's generally a bad shot.
130
395137
3940
Ako stojim daleko okružen
odbranom, to je generalno loša pozicija.
odbranom, to je generalno loša pozicija.
06:51
But we never knew how good "good" was,
or how bad "bad" was quantitatively.
or how bad "bad" was quantitatively.
131
399101
4876
Međutim, nikad kvantitativno nismo znali
koliko je stvarno dobra ili loša.
koliko je stvarno dobra ili loša.
06:56
Until now.
132
404209
1150
Do sada.
06:57
So what we can do, again,
using spatiotemporal features,
using spatiotemporal features,
133
405771
3058
Opet, ono što možemo uraditi,
koristeći spaciotemporalne podatke,
koristeći spaciotemporalne podatke,
07:00
we looked at every shot.
134
408853
1374
je da pogledamo svaki šut.
07:02
We can see: Where is the shot?
What's the angle to the basket?
What's the angle to the basket?
135
410251
3005
Možemo videti: Odakle ide?
Pod kojim uglom je od koša?
Pod kojim uglom je od koša?
07:05
Where are the defenders standing?
What are their distances?
What are their distances?
136
413280
2762
Gde stoji odbrana?
Na kojoj su udaljenosti?
Na kojoj su udaljenosti?
07:08
What are their angles?
137
416066
1331
Pod kojim su oni uglom?
07:09
For multiple defenders, we can look
at how the player's moving
at how the player's moving
138
417421
2977
Za više odbrambenih igrača, možemo videti
kako se igrač kreće
kako se igrač kreće
07:12
and predict the shot type.
139
420422
1433
i predvideti vrstu šuta.
07:13
We can look at all their velocities
and we can build a model that predicts
and we can build a model that predicts
140
421879
4074
Možemo videti svačiju brzinu
i možemo napraviti model koji predviđa
i možemo napraviti model koji predviđa
07:17
what is the likelihood that this shot
would go in under these circumstances?
would go in under these circumstances?
141
425977
4052
koja je verovatnoća da će ovaj šut
ući pod ovim okolnostima?
ući pod ovim okolnostima?
07:22
So why is this important?
142
430188
1500
Zašto je ovo važno?
07:24
We can take something that was shooting,
143
432102
2803
Možemo uzeti neki šut,
07:26
which was one thing before,
and turn it into two things:
and turn it into two things:
144
434929
2680
ranije gledan kao celina,
i podeliti ga na dve stvari:
i podeliti ga na dve stvari:
07:29
the quality of the shot
and the quality of the shooter.
and the quality of the shooter.
145
437633
2651
kvalitet šuta i kvalitet igrača.
07:33
So here's a bubble chart,
because what's TED without a bubble chart?
because what's TED without a bubble chart?
146
441680
3262
I ovde imamo grafikon sa mehurićima,
jer šta bi bio TED bez toga?
jer šta bi bio TED bez toga?
07:36
(Laughter)
147
444966
1014
(Smeh)
07:38
Those are NBA players.
148
446004
1311
Ovo su NBA igrači.
07:39
The size is the size of the player
and the color is the position.
and the color is the position.
149
447339
3120
Veličina je veličina igrača
a boja je njegova pozicija.
a boja je njegova pozicija.
07:42
On the x-axis,
we have the shot probability.
we have the shot probability.
150
450483
2132
Na x-osi, imamo verovatnoću pogotka.
07:44
People on the left take difficult shots,
151
452639
1953
Ljudi s leva šutiraju iz teške pozicije,
07:46
on the right, they take easy shots.
152
454616
2229
sa desna, iz lakih pozicija.
07:49
On the [y-axis] is their shooting ability.
153
457194
2057
Na y-osi je njihov procenat pogotka.
07:51
People who are good are at the top,
bad at the bottom.
bad at the bottom.
154
459275
2562
Ljudi koji su dobri su pri vrhu,
loši pri dnu.
loši pri dnu.
07:53
So for example, if there was a player
155
461861
1760
Tako na primer, vidite igrača
07:55
who generally made
47 percent of their shots,
47 percent of their shots,
156
463621
2097
koji generalno ima 47 procenat šuta,
07:57
that's all you knew before.
157
465718
1389
i to je sve što ste znali.
07:59
But today, I can tell you that player
takes shots that an average NBA player
takes shots that an average NBA player
158
467345
4850
Ali danas, mogu da vam kažem da igrač
šutira onako kako bi prosečan NBA igrač
šutira onako kako bi prosečan NBA igrač
08:04
would make 49 percent of the time,
159
472219
1961
šutirao 49 posto vremena,
08:06
and they are two percent worse.
160
474204
1684
i gore je za dva procenta.
08:08
And the reason that's important
is that there are lots of 47s out there.
is that there are lots of 47s out there.
161
476266
4515
A razlog što je ovo važno je
što ovde ima dosta onih sa 47%.
što ovde ima dosta onih sa 47%.
08:13
And so it's really important to know
162
481714
2549
I tako je vrlo važno znati
08:16
if the 47 that you're considering
giving 100 million dollars to
giving 100 million dollars to
163
484287
3956
da li je onaj sa 47 kome razmišljate
da platite 100 miliona dolara
da platite 100 miliona dolara
08:20
is a good shooter who takes bad shots
164
488267
3055
dobar šuter iz teških pozciija,
08:23
or a bad shooter who takes good shots.
165
491346
2397
ili loš šuter koji pogađa lake koševe.
08:27
Machine understanding doesn't just change
how we look at players,
how we look at players,
166
495130
3333
Mašina ne utiče na naš pogled na igrače,
08:30
it changes how we look at the game.
167
498487
1858
već utiče na naš pogled na igru.
08:32
So there was this very exciting game
a couple of years ago, in the NBA finals.
a couple of years ago, in the NBA finals.
168
500369
3755
Tako je pre par godina, u NBA finalu,
bila jedna vrlo zanimljiva utakmica.
bila jedna vrlo zanimljiva utakmica.
08:36
Miami was down by three,
there was 20 seconds left.
there was 20 seconds left.
169
504148
3207
Majami je gubio sa tri razlike,
20 sekundi pre kraja.
20 sekundi pre kraja.
08:39
They were about to lose the championship.
170
507379
2025
Bili su na pragu da izgube titulu.
08:41
A gentleman named LeBron James
came up and he took a three to tie.
came up and he took a three to tie.
171
509428
3341
Gospodin po imenu LeBron Džejms
je ušao i pucao trojku za izjednačenje.
je ušao i pucao trojku za izjednačenje.
08:44
He missed.
172
512793
1198
Promašio je.
08:46
His teammate Chris Bosh got a rebound,
173
514015
1837
Njegov saigrač Kris Boš skače i brani,
08:47
passed it to another teammate
named Ray Allen.
named Ray Allen.
174
515876
2159
pruža loptu saigraču, Reju Alenu.
08:50
He sank a three. It went into overtime.
175
518059
1919
On ubacuje za tri. Idu produžeci.
08:52
They won the game.
They won the championship.
They won the championship.
176
520002
2096
Pobedili su. Osvojili su šampionat.
08:54
It was one of the most exciting
games in basketball.
games in basketball.
177
522122
2444
To je bila jedna od
najuzbudljivijih utakmica.
najuzbudljivijih utakmica.
08:57
And our ability to know
the shot probability for every player
the shot probability for every player
178
525438
3429
I to što možemo da znamo
verovatnoću pogotka svakog igrača
verovatnoću pogotka svakog igrača
09:00
at every second,
179
528891
1188
u svakoj sekundi,
09:02
and the likelihood of them getting
a rebound at every second
a rebound at every second
180
530103
2956
i verovatnoću skoka pod košem
u svakoj sekundi
u svakoj sekundi
09:05
can illuminate this moment in a way
that we never could before.
that we never could before.
181
533083
3443
može da rasvetli ovaj trenutak na način
na koji nikad ranije nismo mogli.
na koji nikad ranije nismo mogli.
09:09
Now unfortunately,
I can't show you that video.
I can't show you that video.
182
537618
2668
Nažalost, sada vam
ne mogu pokazati taj snimak.
ne mogu pokazati taj snimak.
09:12
But for you, we recreated that moment
183
540310
4493
Ali, za vas smo ponovili tu situaciju
09:16
at our weekly basketball game
about 3 weeks ago.
about 3 weeks ago.
184
544827
2336
na našoj nedeljnoj utakmici
pre oko tri sedmice.
pre oko tri sedmice.
09:19
(Laughter)
185
547279
2167
(Smeh)
09:21
And we recreated the tracking
that led to the insights.
that led to the insights.
186
549573
3410
I ponovo smo oživeli putanju
koja je dovela do tog uvida.
koja je dovela do tog uvida.
09:25
So, here is us.
This is Chinatown in Los Angeles,
This is Chinatown in Los Angeles,
187
553199
4255
I, evo nas.
Ovo je Kineska četvrt u Los Anđelesu,
Ovo je Kineska četvrt u Los Anđelesu,
09:29
a park we play at every week,
188
557478
1564
park gde igramo svake nedelje,
09:31
and that's us recreating
the Ray Allen moment
the Ray Allen moment
189
559066
2231
i evo ga ponovo trenutak Reja Alena
09:33
and all the tracking
that's associated with it.
that's associated with it.
190
561321
2229
i svi pokreti u vezi sa tim.
09:36
So, here's the shot.
191
564772
1517
I evo šuta.
09:38
I'm going to show you that moment
192
566313
2516
Pokazaću vam taj trenutak
09:40
and all the insights of that moment.
193
568853
2587
i sve uvide u taj trenutak.
09:43
The only difference is, instead
of the professional players, it's us,
of the professional players, it's us,
194
571464
3730
Jedina razlika je što smo umesto
profesionalnih igrača ovde mi,
profesionalnih igrača ovde mi,
09:47
and instead of a professional
announcer, it's me.
announcer, it's me.
195
575218
2618
a umesto profesionalnog
komentatora, tu sam ja.
komentatora, tu sam ja.
09:49
So, bear with me.
196
577860
1477
Pa ćete morati da me istrpite.
09:53
Miami.
197
581153
1150
Majami.
09:54
Down three.
198
582671
1150
Minus tri.
09:56
Twenty seconds left.
199
584107
1150
Još dvadeset sekundi.
09:59
Jeff brings up the ball.
200
587385
1198
Džef donosi loptu.
10:02
Josh catches, puts up a three!
201
590656
1535
Džoš je hvata, ubacuje trojku!
10:04
[Calculating shot probability]
202
592631
1849
[Računa se verovatnoća pogotka]
10:07
[Shot quality]
203
595278
1150
[Kvalitet šuta]
10:09
[Rebound probability]
204
597048
1785
[Mogućnost odbrane]
10:12
Won't go!
205
600373
1173
Neće ući!
10:13
[Rebound probability]
206
601570
1446
[Verovatnoća odbrane]
10:15
Rebound, Noel.
207
603777
1256
Brani Noel.
10:17
Back to Daria.
208
605057
1150
Vraća do Darije.
10:18
[Shot quality]
209
606509
3365
[Kvalitet šuta]
10:22
Her three-pointer -- bang!
210
610676
1620
Za tri poena - bam!
10:24
Tie game with five seconds left.
211
612320
2197
Izjednačenje pet sekundi pre kraja.
10:26
The crowd goes wild.
212
614880
1618
Publika je u transu.
10:28
(Laughter)
213
616522
1659
(Smeh)
10:30
That's roughly how it happened.
214
618205
1547
Otprilike tako nekako.
10:31
(Applause)
215
619776
1151
(Aplauz)
10:32
Roughly.
216
620951
1175
Otprilike.
10:34
(Applause)
217
622150
1531
(Aplauz)
10:36
That moment had about a nine percent
chance of happening in the NBA
chance of happening in the NBA
218
624121
5484
Taj momenat je imao šansu
od devet procenata da se desi u NBA
od devet procenata da se desi u NBA
10:41
and we know that
and a great many other things.
and a great many other things.
219
629629
2261
i znamo to kao i mnogo drugih stvari.
10:43
I'm not going to tell you how many times
it took us to make that happen.
it took us to make that happen.
220
631914
3491
Neću vam reći iz koliko pokušaja
nam je ovo uspelo.
nam je ovo uspelo.
10:47
(Laughter)
221
635429
1747
(Smeh)
10:49
Okay, I will! It was four.
222
637200
1872
Okej, ipak hoću! Četiri puta.
10:51
(Laughter)
223
639096
1001
(Smeh)
10:52
Way to go, Daria.
224
640121
1165
Svaka čast, Darija.
10:53
But the important thing about that video
225
641647
4263
Ali ono što je važno
u vezi sa ovim snimkom
u vezi sa ovim snimkom
10:57
and the insights we have for every second
of every NBA game -- it's not that.
of every NBA game -- it's not that.
226
645934
4568
i uvidima koje imamo za svaki sekund
svake NBA utakmice - nije to.
svake NBA utakmice - nije to.
11:02
It's the fact you don't have to be
a professional team to track movement.
a professional team to track movement.
227
650639
3929
To je činjenica da ne morate biti
profesionalni tim da bi pratili kretanje.
profesionalni tim da bi pratili kretanje.
11:07
You do not have to be a professional
player to get insights about movement.
player to get insights about movement.
228
655083
3657
Ne morate biti profesionalni igrač
da biste imali uvid u pokrete.
da biste imali uvid u pokrete.
11:10
In fact, it doesn't even have to be about
sports because we're moving everywhere.
sports because we're moving everywhere.
229
658764
3858
U stvari, ne mora uopšte da se radi
o sportu jer se mi krećemo svuda.
o sportu jer se mi krećemo svuda.
11:15
We're moving in our homes,
230
663654
2369
Krećemo se u našim domovima,
11:21
in our offices,
231
669428
1205
u kancelarijama,
11:24
as we shop and we travel
232
672238
2690
dok kupujemo i putujemo
11:29
throughout our cities
233
677318
1253
po gradu
11:32
and around our world.
234
680065
1618
ili po svetu.
11:35
What will we know? What will we learn?
235
683270
2295
Šta ćemo znati? Šta ćemo naučiti?
11:37
Perhaps, instead of identifying
pick-and-rolls,
pick-and-rolls,
236
685589
2305
Možda, umesto identifikovanja
pick-and-rolla,
pick-and-rolla,
11:39
a machine can identify
the moment and let me know
the moment and let me know
237
687918
3010
mašina može da identifikuje
trenutak i da me obavesti
trenutak i da me obavesti
11:42
when my daughter takes her first steps.
238
690952
2059
kada moja ćerka prohoda.
11:45
Which could literally be happening
any second now.
any second now.
239
693035
2536
Što bukvalno može da se
desi svakog trenutka.
desi svakog trenutka.
11:48
Perhaps we can learn to better use
our buildings, better plan our cities.
our buildings, better plan our cities.
240
696140
3697
Možda možemo bolje da koristimo
zgrade, da bolje planiramo gradove.
zgrade, da bolje planiramo gradove.
11:52
I believe that with the development
of the science of moving dots,
of the science of moving dots,
241
700362
4173
Verujem da ćemo se sa razvojem
nauke pokretnih tački,
nauke pokretnih tački,
11:56
we will move better, we will move smarter,
we will move forward.
we will move forward.
242
704559
3643
bolje kretati, pametnije kretati,
kretati napred.
kretati napred.
12:00
Thank you very much.
243
708607
1189
Hvala vam mnogo.
12:01
(Applause)
244
709820
5045
(Aplauz)
ABOUT THE SPEAKER
Rajiv Maheswaran - ResearcherUsing advanced data analysis tools, Rajiv Maheswaran and Second Spectrum help make basketball teams smarter.
Why you should listen
Sports fans can get obsessed with stats about player performance and game-day physics. But basketball, a fluid and fast-moving game, has been tough to understand through numbers. Rajiv Maheswaran is working to change that, by offering pro basketball teams insight into game data to make better decisions. Maheswaran is the CEO and co-founder of Second Spectrum, a startup transforming sports through technology. He is also a Research Assistant Professor at the University of Southern California's Computer Science Department and a Project Leader at the Information Sciences Institute at the USC Viterbi School of Engineering, where he co-directs the Computational Behavior Group.
His research spans various aspects of multi-agent systems and distributed artificial intelligence using decision-theoretic and game-theoretic frameworks and solutions. His current interests focus on data analytics, visualization and real-time interaction to understand behavior in spatiotemporal domains. Like, say, the spatiotemporal domain around a basketball hoop.
Rajiv Maheswaran | Speaker | TED.com