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
坂本勇人選手はいつ通算3,000安打を達成するか? AIに聞いてみました / Hayato S...
Search
Shinichi Nakagawa
PRO
December 13, 2020
Research
1
890
坂本勇人選手はいつ通算3,000安打を達成するか? AIに聞いてみました / Hayato Sakamoto Performance Prediction Using Feature Engineering with Machine Learning and Python
Sports Analytics Meetup #9 2020/12/13 LT
#Baseball #SABRmetrics #ML #Python
Shinichi Nakagawa
PRO
December 13, 2020
Tweet
Share
More Decks by Shinichi Nakagawa
See All by Shinichi Nakagawa
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
100
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
5k
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
2
4.8k
AI・LLM事業部のSREとタスクの自動運転
shinyorke
PRO
0
470
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
3.6k
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
3.4k
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
4.2k
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
85
88k
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
1.5k
Other Decks in Research
See All in Research
Unsupervised Domain Adaptation Architecture Search with Self-Training for Land Cover Mapping
satai
3
210
2021年度-基盤研究B-研究計画調書
trycycle
PRO
0
350
Vision and LanguageからのEmbodied AIとAI for Science
yushiku
PRO
1
560
Combinatorial Search with Generators
kei18
0
980
ロボット学習における大規模検索技術の展開と応用
denkiwakame
1
130
AI in Enterprises - Java and Open Source to the Rescue
ivargrimstad
0
680
AWSで実現した大規模日本語VLM学習用データセット "MOMIJI" 構築パイプライン/buiding-momiji
studio_graph
2
720
Creation and environmental applications of 15-year daily inundation and vegetation maps for Siberia by integrating satellite and meteorological datasets
satai
3
400
不確実性下における目的と手段の統合的探索に向けた連続腕バンディットの応用 / iot70_gp_rff_mab
monochromegane
2
190
引力・斥力を制御可能なランダム部分集合の確率分布
wasyro
0
260
Panopticon: Advancing Any-Sensor Foundation Models for Earth Observation
satai
3
230
なめらかなシステムと運用維持の終わらぬ未来 / dicomo2025_coherently_fittable_system
monochromegane
0
3.8k
Featured
See All Featured
It's Worth the Effort
3n
187
28k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
115
20k
Speed Design
sergeychernyshev
32
1.2k
Docker and Python
trallard
46
3.6k
Into the Great Unknown - MozCon
thekraken
40
2.1k
Principles of Awesome APIs and How to Build Them.
keavy
127
17k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
359
30k
Practical Orchestrator
shlominoach
190
11k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
140
34k
Context Engineering - Making Every Token Count
addyosmani
6
250
We Have a Design System, Now What?
morganepeng
53
7.8k
Fantastic passwords and where to find them - at NoRuKo
philnash
52
3.4k
Transcript
ӫޫͷഎ൪߸6⃣ ࡔຊ༐ਓ3,000ຊ҆ଧه೦LT Shinichi Nakagawa(@shinyorke) Sports Analyst Meetup #9 2020/12/13
ʁʁʁʮ༐ਓ·ͩ2,000ຊ҆ଧΖʯ
ͦͷͱ͓ΓͰ͍͟͝·͢, ࣦྱ͠·ͨ͠
ࡔຊ༐ਓ͍ͭ௨ࢉ3,000ຊ҆ଧΛ ୡ͢Δ͔AIʹฉ͍ͯΈ·ͨ͠ Shinichi Nakagawa(@shinyorke) Sports Analyst Meetup #9 2020/12/13
ຊͷςʔϚ • ࡔຊ༐ਓ͕͍ͭ͝Ζ௨ࢉ3,000ຊ҆ଧΛୡ͢Δ͔༧͢Δ • ਅ໘ͳ, ༧ଌͲ͜·ͰͰ͖Δ͔ࢼͯ͠ΈΔ • ʮӫޫͷഎ൪߸6⃣ࡔຊ༐ਓ3,000ຊ҆ଧͷಓʯ͕ Կޙʹ์ө͞ΕΔ͔Θ͔Δ΄͏͕͍͍ΑͶʢదʣ
Who am I ?ʢ͓લ୭Αʣ • Shinichi Nakagawaʢத ৳Ұʣ • େͷSNSͰʮshinyorkeʢ͠ΜΑʔ͘ʣʯͱ໊͍ͬͯ·͢
• JX Press Corporation Senior Engineer ʢJX௨৴ࣾ γχΞɾΤϯδχΞʣ • Baseball Engineer, Data Scientist ʢੜͷٿΤϯδχΞɾσʔλαΠΤϯςΟετʣ • Ҏલ͓ࣄͰٿΤϯδχΞʮͩͬͨʯਓ
ʲCMʳαʔόʔαΠυΠϯλʔϯืूͯ͠·͢ https://www.wantedly.com/projects/543767 ※ֶੜ͞ΜݶఆͰ͢&ผʹεϙʔπͷࣄͬͯ༁͡Όͳ͍Ͱ͢
26.4ඵͰৼΓฦΔ2020ͷϓϩٿ • ιϑτόϯΫϗʔΫεຊҰʢ4࿈ʣ • όϯςϦϯυʔϜφΰϠ&౦ژυʔϜͷձࣾ(ry • ࡔຊ༐ਓʢڊਓʣ, ӈଧऀͱͯ͠࠷গͰ2,000ຊ҆ଧୡ ͦͷଞʹ͍ͬͺ͍͋Δ͚ͲׂѪʢదʣ
ࡔຊ༐ਓબखͳΒ3,000ຊ҆ଧ༨༟Ͱ • 31ࡀ10ϲ݄Ͱͷୡӈଧऀ࠷ • গͳ͘ͱ͋ͱ4, 5ݱ͢ΔͰ͠ΐ γϣʔτͰݩؾʹΠέͯ·͢͠. • ͡Ό͍͋ͭࠒ3,000ຊ҆ଧΔͷ͞?
͜Εͬͯաڈͷσʔλ͔Β͏·͍۩߹ʹΕ༧ଌՄೳͰ? https://www.nikkansports.com/baseball/news/202011080000831.html
ͱ͍͏Θ͚Ͱ༧ଌϞσϧΛ࡞Γ·ͨ͠. ࠓճPyCon JP 2020ͰͬͨͭΛݩʹͪΐͬͱΞϨϯδͯ͠࡞Γ·ͨ͠. https://shinyorke.hatenablog.com/entry/baseball-and-ml-with-python
ࠓճͷΞϓϩʔνʢΊͬͪΌཁʣ • ϝδϟʔϦʔάͷσʔλΛͬͯ 1.࠷ۙ୳ࡧܥͷΞϧΰϦζϜͰ͍ۙબख୳͠ 2.֬ʢͬΆ͍ʣํ๏Ͱ༧ଌΛ࡞Δ • ↑ͷ݁ՌΛStreamlitͰՄࢹԽ
ͳͥϝδϟʔͷσʔλͳͷ͔ • 3,000ຊ҆ଧୡऀ, ຊϓϩٿҰਓ͔͍͠ͳ͍ʢ͠ʣ ※ʮ୭Ͱ͔͢ʁʯ࣭ͬͯ׃ͧ • ϝδϟʔେਖ਼ٛΠνϩʔ༷ଞ, 3,000ຊ҆ଧୡऀ͕ଟ͍. •
σʔλͷϥΠηϯε&εΫϨΠϐϯάͱ͔େมͰ͠ΐ.
ࡔຊ༐ਓʹ͍ۙϝδϟʔϦʔΨʔ ࢲʢshinyorkeʣ࡞, ʮzobristʯϞσϧͰग़ͨ݁͠Ռʢ΄΅ANNͰ͢ʣ ϝδϟʔϦʔάΛͬͯΔਓ͔ΒΈΔͱೲಘͷ݁ՌͩͱࢥΘΕ ໊͓લνʔϜ ʢ௨ࢉʣ ଧຊྥଧ௨ࢉ҆ଧ ಛͱ͔ 9BOEFS#PHBFSUT
ʢ3FE4PYʣ ଧ੮ӈଧ ௨ࢉ014 ݱ۶ࢦͷ߈ܸܕγϣʔτ %FSFL+FUFS ʢ:BOLFFTʣ ଧ੮ӈଧ આ໌ෆཁͷελʔ खʹݶΔͱ௨ࢉ҆ଧҐ 5SPZ5VMPXJU[LJ ʢ3PDLJFT FUDʜʣ ଧ੮ӈଧ ௨ࢉ014 ߈ܸܕγϣʔτ ͳ͓ຊڌ +JNNZ3PMMJOT ʢ1IJMMJFT FUDʜʣ ଧ੮྆ଧ कඋܕͳγϣʔτ ࣮ಇͷແࣄ೭໊അ
σϞ͠·͢
ࡔຊ༐ਓͷࠓޙ - ҆ଧɾຊྥଧɾଧ ࣅ͍ͯΔϝδϟʔϦʔΨʔXਓͷΛ75%λΠϧͰࢉग़
ࡔຊ༐ਓͷࠓޙ - ଧ ࣅ͍ͯΔϝδϟʔϦʔΨʔXਓͷΛ75%λΠϧͰࢉग़
ࡔຊ༐ਓͷࠓޙΛ·ͱΊΔͱ 2027ʢ38ࡀʣ·Ͱنఆଧ֬อͰ͖ΔͬΆ͍. ※نఆଧ443ଧ੮ʢ2019ͷࢼ߹143×3.1Ͱܭࢉ, ࢛ࣺޒೖʣ ྸ ଧ ҆ଧ ຊྥଧ
ଧ ଧ
ࡔຊ༐ਓબख, ௨ࢉʢ༧ଌʣ ͜ΕͰγϣʔτͩͬͨΒڧ͗͢Ͱʢ͑ʣ ظؒ ଧ ҆ଧ ຊྥଧ ଧ ଧ ·Ͱ
˞ݱ࣮ ˞༧ଌ ௨ࢉʢ༧ଌʣ
ߟ • 39ࡀ͝Ζʹ3,000ຊ҆ଧୡ…ͷϖʔε·͋·͋͋Γͦ͏. ͨͩ͠ྼԽආ͚ΒΕͳ͍. • 36ࡀ͔ΒͷٸܹྼԽकඋҐஔมߋͱ͔ͰઌԆ͠Ͱ͖ͦ͏. ʲࢀߟʳѨ෦৻೭ॿ36ࡀ͔Βัख->ϑΝʔετʹίϯόʔτ •
௨ࢉຊྥଧʢ༧ଌʣ321ຊ…334ຊߦͬͯཉ͍͚͠ͲͲ͏͔
͜ͷ͓͠·͍Ͱ͢…͕ʂʁ • ༧ଌϞσϧ࡞ΓηΠόʔϝτϦΫεແ͠ͰͰ͖ͳ͔ͬͨ • ʮRʹΑΔηΠόʔϝτϦΫεೖʯग़ͨ͠, ͜ͷลΛಛྔΤϯδχΞϦϯάతʹৼΓฦΓ͍ͨ • ͍ͬͯ͏ϩϯάτʔΫ͕Ͱ͖ͨΒ͍͍ͳ⚾
ʢҙ༁ɿࠓճંͬͨϞσϧͷΛ͍ͨ͠ʣ ӡӦͷօ༷, ͝ݕ౼ΑΖ͓͘͠ئ͍͠·͢
ήʔϜηοτ⚾ ͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠. Shinichi Nakagawa(Twitter/Facebook/etc… @shinyorke)