Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
野球エンジニアの72万球 #BPStudy
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Shinichi Nakagawa
PRO
March 29, 2018
Research
2.6k
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
野球エンジニアの72万球 #BPStudy
Baseballsavantを例とした可視化と簡単な分析事例です
Shinichi Nakagawa
PRO
March 29, 2018
More Decks by Shinichi Nakagawa
See All by Shinichi Nakagawa
LLMの出力を"いい感じに"する技術 / Taming LLM Output: AI Agent Design Patterns with FastAPI
shinyorke
PRO
4
2.3k
野球解説AI Agentを開発してみた - 2026/02/27 LayerX社内LT会資料
shinyorke
PRO
0
750
WBCの解説は生成AIにやらせよう - 生成AIで野球解説者AI Agentを実現する / Baseball Commentator AI Agent for Gemini
shinyorke
PRO
1
760
自らを強いエンジニアにするための3つの習慣 2025/ Fitter happier more productive
shinyorke
PRO
0
330
生成AI時代におけるSREの進化とキャリア戦略 / Building an Embedded SRE team and my career
shinyorke
PRO
0
190
生成AIを活用した野球データ分析 - メジャーリーグ編 / Baseball Analytics for Gen AI
shinyorke
PRO
1
6.8k
ゼロから始めるSREの事業貢献 - 生成AI時代のSRE成長戦略と実践 / Starting SRE from Day One
shinyorke
PRO
3
9.8k
AI・LLM事業部のSREとタスクの自動運転
shinyorke
PRO
0
600
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
5k
Other Decks in Research
See All in Research
JPA2026_NetworkTutorial_JunKashihara
junkashihara
0
230
敵対生成プロンプト同時探索による内省型プロンプト最適化
kinoue_smarthr
0
440
Language and AI
ayaniwa
0
320
最先端NLP 2026 論文紹介: Wait, Wait, Wait... Why Do Reasoning Models Loop? / SNLP Paper Review: Wait, Wait, Wait... Why Do Reasoning Models Loop?
tkng
0
260
OWASP AISVS - C7
shiell
2
830
XDPerf: A High-Performance Traffic Generator Built with WASM and eBPF
takehaya
1
340
医療LLMの現在地〜最新研究から社会実装までを考える〜
kento1109
1
1.8k
全国町字単位空き家率推定データver1.0データ仕様
microbaseinc
0
290
適応的スパムフィルタのための軽量な類似メッセージカウンタ / jsai2026-adaptive-spam-filter
monochromegane
0
5.9k
実例から見るLLMのマンガ理解:実務VQAタスクによる長期的文脈と視覚情報の定性評価
kzmssk
0
190
超効率化への挑戦:1bit LLMの現状と展望
yumaichikawa
0
860
完全自律LLMエージェントでDIVER OSINT CTF 2026に挑戦してみた
analokmaus
0
770
Featured
See All Featured
AI Search: Where Are We & What Can We Do About It?
aleyda
0
8.1k
Visual Storytelling: How to be a Superhuman Communicator
reverentgeek
2
710
The #1 spot is gone: here's how to win anyway
tamaranovitovic
4
1.2k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
46
3k
How to Think Like a Performance Engineer
csswizardry
28
2.9k
Why Your Marketing Sucks and What You Can Do About It - Sophie Logan
marketingsoph
0
430
Building Applications with DynamoDB
mza
96
7.2k
Paper Plane
katiecoart
PRO
5
54k
Leveraging Curiosity to Care for An Aging Population
cassininazir
1
530
Tell your own story through comics
letsgokoyo
1
1.1k
The Limits of Empathy - UXLibs8
cassininazir
2
720
A Soul's Torment
seathinner
8
3.7k
Transcript
ٿΤϯδχΞͷ72ສٿ τϥοΩϯάɾσʔλ͔ΒޠΔٿϊϯϑΟΫγϣϯ Shinichi Nakagawa@shinyorke
ٿΤϯδχΞis୭?
ʲʳϫΠͰ͢ • Shinichi Nakagawa(த৳Ұ) • ωΫετϕʔε CTO/ٿΤϯδχΞ • #ηΠόʔϝτϦΫε #Python
#σʔλੳ • Baseball Play Study ։͔࢝࣌Βৗ࿈(2014ʙ) • Baseball Play Study͔Βϗϯτʹٿքʹདྷ·ͨ͠
ʁʁʁʮ72ສٿ͛ͨΒݞග͕(ryʯ ※͛ͯͳ͍Ͱ͢w
72ສٿ=MLBͷ1γʔζϯٿ 2017ͷ࣮,ϨΪϡϥʔγʔζϯͷΈ. ϓϨʔΦϑΛؚΊΔͱ73ສٿͪΐͬͱʹͳΔ.
Ͳ͜ʹσʔλ͋Δͷ? • MLBެࣜʮBaseballsavantʯͱ͍͏αΠτͰ ୭ͰೖखͰ͖Δ • https://baseballsavant.mlb.com/ statcast_search • τϥοΫϚϯɾStatcastͰهͨ͠ τϥοΩϯάɾσʔλ͕ݩʹͳ͍ͬͯΔ
τϥοΫϚϯ=ٿɾଧٿͷܭଌػث ͘Θ͘͠ʮBaseball GeeksʯͷղઆΛͲ͏ͧʂ https://www.baseballgeeks.jp/?p=3551
ࠓͷςʔϚʮଧٿʯ • 72ສٿ͔Βબग़ͨ͠ʮҹతͳଧٿʯΛհ • ຊͱ͍,ϝδϟʔͷϨδΣϯυ͞Μ • ࠓ͔ΒೋྲྀͰߦ͘ਓ…ͷಉ྅ • งғؾΛ௫ΜͰ͘ΕΔͱ͋Γ͕͍ͨͰ͢
128,945 / 718,917(ٿ) ※શσʔλͷ18%Λ༻(͓͓Αͦ100MB͘Β͍)
ʲਤʳશଧٿσʔλͷ݁Ռ(2017) X(ԣ)ɿଧٿ, Y(ॎ)ɿଧٿ֯
ʲਤʳશଧٿσʔλͷ݁Ռ(2017) X(ԣ)ɿଧٿ, Y(ॎ)ɿଧٿ֯ ଧκʔϯ
ʲਤʳશଧٿσʔλͷ݁Ռ(2017) X(ԣ)ɿଧٿ, Y(ॎ)ɿଧٿ֯ ଧκʔϯ ୯ଧκʔϯ
ʲਤʳશଧٿσʔλͷ݁Ռ(2017) X(ԣ)ɿଧٿ, Y(ॎ)ɿଧٿ֯ ଧκʔϯ ୯ଧκʔϯ खͷ͓ࣄκʔϯ
ʲਤʳશଧٿσʔλͷ݁Ռ(2017) X(ԣ)ɿଧٿ, Y(ॎ)ɿଧٿ֯ ଧκʔϯ ୯ଧκʔϯ ্͕Γ͗͌͢ खͷ͓ࣄκʔϯ
֮͑ͯ΄͍͜͠ͱ • ͍͍ײ͡ͷʮଧٿʯʮඈᠳ֯ʯͰඈͿଧٿϗʔϜϥϯɾଧʹͳΔՄೳੑ͕ߴ͍ • ҆ • 187km/h / 8~50 •
161km/h / 24~33 • 158km/h / 26~30 • ͜ΕΛʮόϨϧκʔϯʯͱ͍͍·͢ • ʁʁʁʮڈϑϥΠϘʔϧɾϨϘϦϡʔγϣϯ͕͋ͬͨ͡Όͳ͍ɺͦΕ(ryʯ ˠਖ਼ղʂͦ͏͍͏͜ͱͰ͢ • ʲࢀߟจݙʳ https://www.baseballgeeks.jp/?p=1342 ※Baseball GeeksΑΓҾ༻
ೋਓͷଧऀʹ͍ͭͯ • ຊͱ͍,ϝδϟʔͷϨδΣϯυ͞Μ • ࠓ͔ΒೋྲྀͰߦ͘ਓ…ͷಉ྅ • ͜ͷೋਓͷଧٿΛݟͯΈΑ͏
ҰਓʮIchiro Suzukiʯ ϚϦφʔζ෮ؼ͓ΊͰͱ͏͍͟͝·͢ʂ ը૾ɿ https://commons.wikimedia.org/wiki/File:Ichiro_Suzuki_2010.jpg
ʲਤʳIchiro Suzukiબखͷଧٿ(2017) X(ԣ)ɿଧٿ, Y(ॎ)ɿଧٿ֯
ʲਤʳIchiro Suzukiબखͷଧٿ(2017) X(ԣ)ɿଧٿ, Y(ॎ)ɿଧٿ֯ ͜ͷล͕ ଧκʔϯ
ʲਤʳIchiro Suzukiબखͷଧٿ(2017) X(ԣ)ɿଧٿ, Y(ॎ)ɿଧٿ֯ ͜ͷล͕ ଧκʔϯ όϨϧ ൃݟʂ
ΠνϩʔબखͷόϨϧ • 2017/8/22 ϑΟϦʔζઓ(ఢͰͷࢼ߹) • ୈ3߸ιϩ,ઌൃͷϊϥ͔ΒҰൃ • 160.48 km/h, 28
• શ3ຊͷΞʔνத,όϨϧೖΓ͜ͷ1ຊͷΈ …Ͱ͚͢Ͳ,͜Ε͕40ͱ͔ා͍(ଚܟͷ؟ࠩ͠)
ೋਓʮMike Troutʯ େ୩ᠳฏ(ΤϯδΣϧε)ͷಉ྅͔ͭεʔύʔελʔ ը૾ɿ https://commons.wikimedia.org/wiki/File:Los_Angeles_Angels_center_fielder_Mike_Trout_(27)_(5972457428).jpg
Mike Trout #ͱ ※೦ͷҝ • ϝδϟʔΛද͢ΔελʔͷҰਓ • ϩαϯθϧεɾΤϯθϧεͷ֎ख(ηϯλʔ) • ӈ͛ӈଧͪ,26ࡀ,ϝδϟʔ8
• ߈कࡾഥࢠ͕ʮຊʹʯἧ໊ͬͨબख • ௨ࢉOPS .976ɹ˞Ϊʔλ(ιϑτόϯΫ).946
ʲਤʳMike Troutબखͷଧٿ(2017) X(ԣ)ɿଧٿ, Y(ॎ)ɿଧٿ֯
ʲਤʳMike Troutબखͷଧٿ(2017) X(ԣ)ɿଧٿ, Y(ॎ)ɿଧٿ֯ ͜ͷล͕ଧκʔϯ ˠϗʔϜϥϯଟ͗͌͢
ʲਤʳMike Troutબखͷଧٿ(2017) X(ԣ)ɿଧٿ, Y(ॎ)ɿଧٿ֯ ͜ͷล͕ଧκʔϯ ˠϗʔϜϥϯଟ͗͌͢ όϨϧ͚ͩͲ Ξτͩͱʁ
Ξτʹͳͬͨଧٿͷৄࡉ X(ԣ)ɿଧٿ, Y(ॎ)ɿଧٿ֯
͜Ε͍͢͝ϓϨʔͳͷͰʁ • ͱࢥ͍,ࢼ߹݁ՌΛνΣοΫ • هɿηϯλʔϑϥΠ • ϑΝΠϯϓϨʔͱ͍͏هͳ͘ • ී௨ͷଧٿͱͯ͠ͱΒΕ͍ͯͨ •
ϝονϟྑ͍͋ͨΓͷਅਖ਼໘ͩͬͨʁʁʁ ;ʔΜ(ಡΈ)
·ͱΊ • ϝδϟʔϦʔάଧٿɾٿͷσʔλ͕ϑΝϯͰ͑Δ • ଧٿͱ֯ʹண͢Δ͚ͩͰ৭ʑͳࢹ͕Ͱ͖Δ • Πνϩʔબख·ͩ·͔ͩͬͱͤΔ (ελΠϧม͑ͯ͘Εͳ͍͔ͳ͋ʁ) • େ୩ᠳฏ͕͛Δͱ͖τϥτʹͯ͠Ͷ
• ࢸͬͯී௨ͷϑϥΠ࣮ී௨͡Όͳ͍Մೳੑ͕
τϥοΩϯάɾσʔλ ָ͘͠ͳ͖͔ͬͯͨͳʁ
Baseball GeeksͰͬͱָ͘͠! • τϥοΩϯάɾσʔλΛ׆༻ͨ͠ٿͷ৽͍͠ݟํɾࢹΛհͯ͠·͢ • σʔλɾεϙʔπՊֶͰ໌Β͔ʹͳͬͨ͜ͱΛʮΘ͔Γ͘͢ʯ͑Δ • ΈΜͳಡΜͰͶ&ϒΫϚΑΖ͘͠ʂ https://www.baseballgeeks.jp/
ϓϨΠϘʔϧʂ ࠓٿͰྑ͍ҰΛʂ͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠⽁ Shinichi Nakagawa(Twitter/Facebook/etc… @shinyorke)