Slide 1

Slide 1 text

No content

Slide 2

Slide 2 text

No content

Slide 3

Slide 3 text

    

Slide 4

Slide 4 text

LINE DEVELOPER DAY • A • A • https://linedevday.linecorp.com/jp/2018/

Slide 5

Slide 5 text

 

Slide 6

Slide 6 text



Slide 7

Slide 7 text

 •N L D :@ • T • E I • 7

Slide 8

Slide 8 text



Slide 9

Slide 9 text

DataLabs • • • • N I • • LE

Slide 10

Slide 10 text

 in Data Labs                   

Slide 11

Slide 11 text



Slide 12

Slide 12 text



Slide 13

Slide 13 text

 • 741,-<6+38 $D?BR-<29* /:;*=L&! $  • #%TA0.<5GXF@'NP $ Y&  H>(U)  • MIS741,-<6+38)    O& • QC"JVK V(EW

Slide 14

Slide 14 text

 • c )A d • Nc cR a c Vw x C c aVc nle nr o ))+ iB • c V c E E • V c E E

Slide 15

Slide 15 text

   • !$( • '#%&  • # %  (  " https://www.recruit.co.jp/newsroom/2018/0426_18161.html 

Slide 16

Slide 16 text

   • • • ! 0

Slide 17

Slide 17 text

     https://www.jil.go.jp/kokunai/statistics/timeseries/html/g0301.html 

Slide 18

Slide 18 text

"!&#  ,4(  •             https://www.recruit.co.jp/newsroom/2018/0426_18161.html  7-/ 8  %$  2 16 3 *.)  '50 + 

Slide 19

Slide 19 text

      • 2 8 ( • 0 4 2 http://wesmckinney.com/pages/about.html  From August 2007 to July 2010, I worked on the front office quant research team at AQR Capital Management, a large quantitative investment manager in Greenwich, CT. During this time, I led a very successful effort to migrate research and production model building and research processes to the Python programming language. I started building pandas on April 6, 2008, as part of a skunkworks effort to reproduce some econometric research in Python. As part of my work, we formed a new Research Development team for the global macro group to drive software innovation in the front office.

Slide 20

Slide 20 text

 https://www.nikkei.com/article/DGXMZO37559930Z01C18A1000000/

Slide 21

Slide 21 text

 •    

Slide 22

Slide 22 text

      • !  •  "  # Lutz, Mark. Learning Python: Powerful Object-Oriented Programming. “ O‘Reilly Media, Inc. 

Slide 23

Slide 23 text

      •     • / • • • /

Slide 24

Slide 24 text

      • +&*'#, SV--0P :!! "2 #, • $.%-3B5Q LKFT  8;NRU)(6@A  IEC 4?1T3B=7MO J 

Slide 25

Slide 25 text

 →  • •  l a  ! • i RV S N • ts NG

Slide 26

Slide 26 text

→   • 1 • S W 0 G 2 • W P A C 2 2 2 4 • S W • @4 2 4

Slide 27

Slide 27 text

   https://www.slideshare.net/RecruitLifestyle/cet-capture-everything

Slide 28

Slide 28 text

     • ! % •     • % % U % X % X

Slide 29

Slide 29 text

 → DataLabs •     •    https://www.ipsj.or.jp/event/sj/sj2019/Bigdata.html 

Slide 30

Slide 30 text

 → DataLabs •  &% *   •  (') -!    ,+  "$#  •     

Slide 31

Slide 31 text

How LINE Corp Use to Compete in a Data-Driven World •&$ ( •#%"!*)  '  •     

Slide 32

Slide 32 text

Ad   Something • N B A • 0 () () • 1 & He, Xinran, et al. "Practical lessons from predicting clicks on ads at facebook." Proceedings of the Eighth International Workshop on Data Mining for Online Advertising. ACM, 2014.

Slide 33

Slide 33 text

 • O  • !  • K •

Slide 34

Slide 34 text

THANK YOU