A4 /0 2T
1 4
A D1 A 9 D2 0
9 9
A 9
GI
2
ü
ü
ü
ü
ü
3
2
4
3
1
5
K
6
)(
4
ATeAT a
RTs E i i
t / t p s a s g
• (. ) . H N s L
• s N
• Nv
• ( : : N
• /-/ N
• coRh L (. ) .
• C V s m LirgS nd I N
A dpa V D
2015 2016 P4 1 0 0
( )
8
2
8
6
2
4
3
1
5
K
6
7y / - - - - - - :/ - -
b aL L s t w l u L
- - .- - C
ü D D
ü D
ü
ü f aho
ü
ü co
ü racs
ü cp s
ü c os
ü cS
ü cS D
ü it
ü c y
ü un f
ü c
ü e t
ü
ü c k a
ü c s
ü cL
ü c
ü c f d
S B
IL B
I
8/ - - - - - - :/ - -
d ac L uo l n w
S - - .- - I I S
ü S S
ü S
ü
ü h c l
ü
ü i e l
ü tceu
ü i eriu
ü i e a u
ü i e S
ü i e S
ü b k
ü i e
ü wp h
ü i e
ü
ü
ü i e c
ü i e u l
ü i e
ü i e
ü i e h fs
y DD
C
B C
L
9
2
4
3
1
5
K
6
10
w 9DDA : :2 ( ) 92D :776 6 6 2 D:7: :2 : D6 : 6 6 2 9: 6 62 : 66A 62 : 2:
v 02 9: 6 /62 : -66A /62 :
g av aM bh fc g
v aI_ av M . L . _I c
9DDA 2: 2 2: A : 1
va d e
i kspr la
n lijs mo
i at n l
e i w
c g
11f 0::7 - 3 / : . 8 - 0 .: :0- 13 1 / 3 2 . 01 - 3- 8 1 / r gide m
o n
u
n
u
n
pmn
htr
ac
ld c b o n o n ks
h
12g 0::7 - 3 / : . 8 - 0 .: :0- 13 1 / 3 2 . 01 - 3- 8 1 / s h ef n
p o
oo
no
k
ius r
a
bd
me d c p o p o lt
i
13
loan_amnt annual_inc int_rate term emp_title emp_length home_ownership addr_state last_pymnt_d loan_condition
30000 100,000.00 22.35 36 months Supervisor 5 years MORTGAGE CA Jan-19 Good Loan
40000 45,000.00 16.14 60 months
Assistant to
the Treasurer
(Payroll)
< 1 year MORTGAGE OH Feb-19 Good Loan
8000 55,000.00 6.46 36 months Meat Cutter 10+ years MORTGAGE WA NaN Bad Loan
iy :: 4/ - / : 4/ . -4 . : 4
200
/ . 4 ( : u ) -/4 Cd np E cC bCegcC
o mw slL h ad mwcC x t cC k
6000 17,000.00 14.47 36 months NaN NaN MORTGAGE FL NaN
7500 50,000.00 12.73 36 months NaN NaN MORTGAGE IN Oct-18
30000 109,000.00 20.89 36 months President 8 years MORTGAGE TX Feb-19
D D
cC x D
14
ü
ü
ü e
ü
x
15
https://www.pfmjournal.org/m/journal/view.php?number=32
D 5
D 5
D L
https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-
convolutional-neural-networks
5
( )
(!) ("# ) (#)
(
(!) ("# )
(
(
( )
(
17
2
4
3
1
5
K
6
1
whP a c l
l n t a c t
mD a c
gkP a c gk CU
i gk pD Po
a c P K e j
w P p a c s
0:: 3 // . 5 0:: 1/ :. 2
Performance Tiers
19
https://www.kaggle.com/progression
Master
Expert
Contributor
Novice
171 (0.1%)
1,347 (1.1%)
4,974 (3.9%)
52,012 (41.3%)
67,476 (53.6%)
SS
S
A
B
Grandmaster
Grandmaster
Master
Expert
https://dena.ai/kaggle/
Competition Medals
) > ) 9 2
( 0)1 1 0 1 K
/
.. /
21
Kaggle 2019 11 125,564 627 (top 0.5%)
SIGNATE
ü 2
https://www.slideshare.net/matsukenbook/signate-108228406
o a
g t t
/
a
(
ü b
ü
ü g
g
ü l
ü e
ü ü
ü
ü g
ü ( k
) ))
e
N K
o
mP .24463 e n i t
Bv e g L e _
K
e
_
e
095 2 3 /
e _
r
23
:391
.3872 :
:391
:391
:391
:391
:391
3
2
u l
ü s
a
ü
24
https://www.kaggle.com/c/PLAsTiCC-2018
25
https://www.kaggle.com/michaelapers/the-plasticc-astronomy-starter-kit
2019 15
+ 15+ 4
0
https://www.kaggle.com/michaelapers/the-plasticc-astronomy-starter-kit
https://arxiv.org/pdf/1903.11756.pdf
https://en.wikipedia.org/wiki/Type_Ia_supernova
5 9
https://www.quantamagazine.org/variable-stars-have-strange-nonchaotic-attractors-20150310
: 3 9
27
ü . D0 D 48
ü D 7 1
ü D .
ü 5
D 0
3
I
D
28
0
https://www.kaggle.com/kenmatsu4/feature-engineering-with-gaussian-process
1 2
2
29
Gaussian Process
https://www.kaggle.com/kenmatsu4/feature-engineering-with-gaussian-process
30
0
https://www.kaggle.com/kenmatsu4/feature-engineering-with-gaussian-process
PLAsTiCC Astronomical Classification
https://www.kaggle.com/c/PLAsTiCC-2018/leaderboard
32
https://www.kaggle.com/c/PLAsTiCC-2018/discussion/70669
5 9
% : 0
100% 3
% 7 0
3
GC E
33
Nc f Wc f c f W SaT W
Quora Insincere Questions
Classification
H
K
I
tp W SC W
t T
M
m e W r i C
/ 39 05 6S M
63
63
D
M
o
i
o
i
u
C yE y T
R 63
s W
p
TW C
Q M 63
b W
iMet Collection 2019 - FGVC6
1W 6 9 3 A 6A 7
W W Mnl
o M
63
W
264W
b
D
34
/
ü l o t u
t u hu u R
ü K u ae D
R M
og pu / KS
og pu S
ü n K
M hu u
ü P S u y
M M
A
35
N
&&
2
4
3
DKN1
A
5
37
// . - -/
I :
A
38
b
b
b
39
DPcm
DPcm k j
SO L a
L
F G I bA d L A ni SO L e
AI E
I H
DC
A
DC E
reMa M
DT i M
M re D DE CH AH
a rd M
I
A d p eL
B /
M
/M
A
M
T
e M
o
p eL B g VD
g e AH M
M
p e H L
L A B
AH re I R
DT M reM A
DT rdnee M
41
a P a
h
ü
ü p h o A
ü
ü P A
ü x
ü iy ED
ü
ü A
ü i
ü x tn ED
ü l a
ü t a
ü i t
ü
ü h
ü A
ü x nrh s
ü a r
p
A
ü P x A p) ) (
A
42
N
&&
2
4
3
DKN1
A
5
43
Ø Gb l a b r
G b m
Ø b
ü d
b n o
ü l
ü b
Ø t s r e
44

データ分析コンテストとデータサイエンティストの働きかた