Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
坂本勇人さん改め山田哲人さんの成績予測をやってみた / Baseball Play Study...
Search
Shinichi Nakagawa
PRO
December 17, 2020
Research
0
2.9k
坂本勇人さん改め山田哲人さんの成績予測をやってみた / Baseball Play Study 2020 Winter
Baseball Play Study 2020冬 LT資料
https://bpstudy.connpass.com/event/197652/
Shinichi Nakagawa
PRO
December 17, 2020
Tweet
Share
More Decks by Shinichi Nakagawa
See All by Shinichi Nakagawa
実践Dash - 手を抜きながら本気で作るデータApplicationの基本と応用 / Dash for Python and Baseball
shinyorke
PRO
2
2.2k
Terraform, GitHub Actions, Cloud Buildでデータ基盤をProvisioningする / Data Platform provisioning for Google Cloud and Terraform
shinyorke
PRO
2
3k
Cloud RunとCloud PubSubでサーバレスなデータ基盤2024 with Terraform / Cloud Run and PubSub with Terraform
shinyorke
PRO
9
3.5k
自らを強いエンジニアにするための3つの習慣 / I need to be myself, I can't be no one else
shinyorke
PRO
82
80k
阪神タイガース優勝のひみつ - Pythonでシュッと調べた件 / SABRmetrics for Python
shinyorke
PRO
1
1.3k
Pythonとクラウドと野球の推し活. / Baseball Data Platform for Python and Google Cloud
shinyorke
PRO
2
2.8k
月額コーヒー3.34杯分のコストでオオタニサンの活躍を見守るデータ基盤のはなし / Pyhack Con
shinyorke
PRO
2
480
俺のDXを実現するためのサーバレスなデータ基盤開発と運用 / Serverless Data Platform and Baseball
shinyorke
PRO
5
12k
機械学習エンジニアが目指すキャリアパスとその実話 / My Journey to Become a ML Engineer
shinyorke
PRO
10
17k
Other Decks in Research
See All in Research
A Segment Anything Model based weakly supervised learning method for crop mapping using Sentinel-2 time series images
satai
3
130
ドローンやICTを活用した持続可能なまちづくりに関する研究
nro2daisuke
0
150
打率7割を実現する、プロダクトディスカバリーの7つの極意(pmconf2024)
geshi0820
0
310
Zipf 白色化:タイプとトークンの区別がもたらす良質な埋め込み空間と損失関数
eumesy
PRO
8
1.3k
IM2024
mamoruk
0
230
渋谷Well-beingアンケート調査結果
shibuyasmartcityassociation
0
400
Neural Fieldの紹介
nnchiba
2
680
VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding
sansan_randd
1
460
【NLPコロキウム】Stepwise Alignment for Constrained Language Model Policy Optimization (NeurIPS 2024)
akifumi_wachi
3
530
ナレッジプロデューサーとしてのミドルマネージャー支援 - MIMIGURI「知識創造室」の事例の考察 -
chiemitaki
0
220
機械学習でヒトの行動を変える
hiromu1996
1
550
LLM 시대의 Compliance: Safety & Security
huffon
0
600
Featured
See All Featured
Build The Right Thing And Hit Your Dates
maggiecrowley
34
2.5k
Writing Fast Ruby
sferik
628
61k
Unsuck your backbone
ammeep
669
57k
Fantastic passwords and where to find them - at NoRuKo
philnash
51
3k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.1k
StorybookのUI Testing Handbookを読んだ
zakiyama
28
5.5k
The Cult of Friendly URLs
andyhume
78
6.2k
Building Better People: How to give real-time feedback that sticks.
wjessup
367
19k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
45
9.4k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
40
2k
Build your cross-platform service in a week with App Engine
jlugia
229
18k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
160
15k
Transcript
ࡔຊ༐ਓ͍ͭ௨ࢉ3,000ຊ҆ଧΛ ୡ͢Δ͔AIʹฉ͍ͯΈ·ͨ͠ Baseball Play Study 2020ౙ - γʔζϯৼΓฦΓεϖγϟϧ 2020/12/17 Shinichi
Nakagawa(@shinyorke)
ϫΠʮઌಉ͡ΛଞॴͰͨ͠Α͏ͳʯ
͋ͬʢ͠ʣ ༵ʹʮSports Analyst Meetup #9ʯͰLTͪ͠Όͬͯ·ͨ͠ https://speakerdeck.com/shinyorke/hayato-sakamoto-performance-prediction-using-feature-engineering-with-machine-learning-and-python
ʲ݁ʳࡔຊ༐ਓબखͷ༧ଌ 39ࡀͷγʔζϯ, ͖ͬͱΈΜͳʹॕ͞ΕΔͰ͠ΐ͏
ʲ݁ʳࡔຊ͞Μ3,000҆ଧ39ࡀ ※2028γʔζϯ, ͋͘·ͰݟࠐΈͰ͢
ΊͰͨ͠ΊͰͨ͠ ͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠
͍͍, ͜ΕͰऴΘΕΜͩΖʢ͑ʣ
ͪΌΜͱωλ, ༻ҙͯ͠·͢
ॕɾࢁాਓ༷ϠΫϧτཹ ظܖظؒͷΛ AIʹ፻ͤ͞ฉ͍ͯΈ·ͨ͠ Baseball Play Study 2020ౙ - γʔζϯৼΓฦΓεϖγϟϧ
2020/12/17 Shinichi Nakagawa(@shinyorke)
ຊͷςʔϚ • ϠΫϧτ͍ຊϓϩٿͷਓؒࠃๅͱݴͬͯաݴͰͳ͍ ࢁాਓબख͕ҰମͲΕ΄ͲͷΛࠓޙ͢ͷ͔͏ • ͿͬͪΌ͚ܖֹۚͷ׆༂͢Δͷ͔?͖ʹͳΔ • ͖͏AI͍ͥͬͯ͢͝Θ͔ͬͯ͘ΕͨΒخ͍͠ʢ͜ͳΈʣ
Who am I ?ʢ͓લ୭Αʣ • Shinichi Nakagawaʢத ৳Ұʣ • େͷSNSͰʮshinyorkeʢ͠ΜΑʔ͘ʣʯͱ໊͍ͬͯ·͢
• JX Press Corporation Senior Engineer ʢJX௨৴ࣾ γχΞɾΤϯδχΞʣ • Baseball Engineer, Data Scientist ʢੜͷٿΤϯδχΞɾσʔλαΠΤϯςΟετʣ • ࣗশʮBaseball Play StudyͷϨδΣϯυʯ, ݩɾϓϩͷٿΤϯδχΞ • ࠷ۙ, 12ٿஂതѪओٛऀʹͳΓ·ͨ͠ʢ͕ݩւಓͳͷͰϋϜ͖ʹͳΔʣ.
ඵͰৼΓฦΔ2020ͷϓϩٿ • όϯςϦϯυʔϜφΰϠ, ര • ౦ژυʔϜબख, Ҡ੶ʢ༧ఆʣ • 26 -
4ʢ͠ʣ • ࢁాਓબख, 7૯ֹ40ԯԁʢਪఆʣͰϠΫϧτཹ
ࢁాਓ͞Μͷ740ԯԁͱ͔͍͏ܖ • เ5ԯԁʢʴΠϯηϯςΟϒʣ×7, Β͍͠. • ϑΝϯΈΜͳخ͍͠Ͱ͠ΐ͏, ϫΠخ͍͠Ͱ͢. • ͏ҰਓͷϫΠʮ40ԯԁͬͯݩ͕औΕΔΜΖ͔ʯ
…ͱ͍͏༁Ͱ, ٿAI͞Μʹฉ͍ͯΈ·ͨ͠.
ࠓճ͏͖͏ͷਓೳ PyCon JP 2020ͰͬͨʔͭΛͦͷ··͍·ͨ͠ʢ#spoana ͱಉ͡Ͱ͢ʣ. https://shinyorke.hatenablog.com/entry/baseball-and-ml-with-python
ͻͱ·ͣ݁ՌΛ͓ݟͤ͠·͢.
ࢁాਓ༷ͷࠓޙ - ҆ଧɾຊྥଧɾଧ 150҆ଧͪΐ͍, 17ʙ19ຊྥଧΛՔ͗ͭͭ, 70ଧҎ্Ք͙
ࢁాਓ༷ͷࠓޙ - ଧ 32, 33ࡀ͋ͨΓͰಥવଧʹ֮Ίͯͯ໘ന͍݁Ռʹ
ࢁాਓ༷ͷࠓޙΛ·ͱΊΔͱ ͜ΕͰͣͬͱηΧϯυͬͯ͘ΕΔͳΒ͗͢͢͝Ͱ ͑?τϦϓϧεϦʔ??͏ʔʔΜ ྸ ଧ ҆ଧ ຊྥଧ ଧ ଧ
ࢁాਓ༷ͷ௨ࢉʢ༧ଌʣ ͜ΕͰηΧϯυͬͯڧ͗͢͠·ͤΜ͔ʢ͑ʣ ظؒ ଧ ҆ଧ ຊྥଧ ଧ ଧ ·Ͱ ˞ݱ࣮
˞༧ଌ ௨ࢉʢ༧ଌʣ
ࢁాਓ༷ͷ௨ࢉʢ༧ଌʣ ͜ΕͰηΧϯυͬͯڧ͗͢͠·ͤΜ͔ʢ͑ʣ ظؒ ଧ ҆ଧ ຊྥଧ ଧ ଧ ·Ͱ ˞ݱ࣮
˞༧ଌ ௨ࢉʢ༧ଌʣ 334ͪΌ͏Μ͔ʔ͍
ࢁాਓ༷2027ʢ34ʣ͕͢ه • ௨ࢉຊྥଧɾଧɾଧͰߴकಓࢯΛ͑Δ • ௨ࢉ2,236҆ଧͰ໊ٿձೖΓ·ͬͨͳ͠ • ໊࣮ͱʹϓϩٿ্࢙࠷ڧͷηΧϯυʹͳΔՄೳੑ
ͱ͍͑Ͱ͢Α • 7ܖதͷτϦϓϧεϦʔʢ3ׂ30ຊྥଧ30౪ྥʣଟແཧ • ਓೳ500ଧ੮Ҏ্Ք͙༧ଌΛ͍ͯ͠Δ͚Ͳ, ਓ༷Ҋ֎ނোͱ͔͋Δͷ͕ͪΐͬͱ৺ • ηΧϯυकඋෛ୲͕͔ͳΓ͋ΔϙδγϣϯͳͷͰ
ଧྗΛ׆͔ͨ͢Ίͷίϯόʔτ͋Δ͔͠Εͳ͍
݁ • ຊҰͷηΧϯυʹͳΓͦ͏ͳͷͰ740ԯͷܖଟଥ • ͱ͍͑େࣄʹͬͯཉ͍͠, ͋ΔҙຯਓؒࠃๅͰ͢͠ • ͘Ε͙ΕମʹؾΛ͚ͭͯؤுͬͯ΄͍͠ʂ
ήʔϜηοτ⚾ ͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠. Shinichi Nakagawa(Twitter/Facebook/etc… @shinyorke)