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
Data Science API
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
Takahiro Yoshinaga
November 21, 2019
Technology
5
2.7k
Data Science API
Data Gateway Talk Vol.4
Takahiro Yoshinaga
November 21, 2019
Tweet
Share
More Decks by Takahiro Yoshinaga
See All by Takahiro Yoshinaga
LINEヤフーでのプライバシーを 保護した機械学習事例紹介
yoshinaga0106
0
12
ビッグデータビジネスによる継続的な価値創造と人材育成
yoshinaga0106
0
140
社内LINE公式アカウント メッセージ送りすぎ問題を データサイエンスで解決する
yoshinaga0106
0
240
[ICML2021 論文読み会] A General Framework For Detecting Anomalous Inputs to DNN Classifiers
yoshinaga0106
0
1.4k
データサイエンティストに同じクエリは二度も通じぬ
yoshinaga0106
2
980
Anomaly Detection in KDD2019
yoshinaga0106
1
420
Data Engineering & Data Analysis #8
yoshinaga0106
1
2.6k
Conversion Prediction Using Multi-task Conditional Attention Networks to Support the Creation of Effective Ad Creatives
yoshinaga0106
0
1.5k
Introduction of Clumpiness
yoshinaga0106
0
170
Other Decks in Technology
See All in Technology
All About Sansan – for New Global Engineers
sansan33
PRO
1
1.3k
MCPでつなぐElasticsearchとLLM - 深夜の障害対応を楽にしたい / Bridging Elasticsearch and LLMs with MCP
sashimimochi
0
160
[CV勉強会@関東 World Model 読み会] Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models (Mousakhan+, NeurIPS 2025)
abemii
0
130
StrandsとNeptuneを使ってナレッジグラフを構築する
yakumo
1
110
仕様書駆動AI開発の実践: Issue→Skill→PRテンプレで 再現性を作る
knishioka
2
640
AIと新時代を切り拓く。これからのSREとメルカリIBISの挑戦
0gm
0
890
Embedded SREの終わりを設計する 「なんとなく」から計画的な自立支援へ
sansantech
PRO
3
2.4k
ブロックテーマ、WordPress でウェブサイトをつくるということ / 2026.02.07 Gifu WordPress Meetup
torounit
0
180
AzureでのIaC - Bicep? Terraform? それ早く言ってよ会議
torumakabe
1
530
配列に見る bash と zsh の違い
kazzpapa3
1
140
OWASP Top 10:2025 リリースと 少しの日本語化にまつわる裏話
okdt
PRO
3
690
SREじゃなかった僕らがenablingを通じて「SRE実践者」になるまでのリアル / SRE Kaigi 2026
aeonpeople
6
2.3k
Featured
See All Featured
Color Theory Basics | Prateek | Gurzu
gurzu
0
200
Unlocking the hidden potential of vector embeddings in international SEO
frankvandijk
0
170
Marketing to machines
jonoalderson
1
4.6k
WCS-LA-2024
lcolladotor
0
450
Navigating Team Friction
lara
192
16k
Everyday Curiosity
cassininazir
0
130
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
141
34k
Mind Mapping
helmedeiros
PRO
0
81
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
52
5.8k
Why Mistakes Are the Best Teachers: Turning Failure into a Pathway for Growth
auna
0
51
Breaking role norms: Why Content Design is so much more than writing copy - Taylor Woolridge
uxyall
0
160
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2k
Transcript
Data Science API 2019/11/21 Takahiro Yoshinaga, LINE Corporation
@t_yoshinaga0106 Takahiro Yoshinaga aI l k IS N X ü
ü Iht S n ü 1 d / n ü 1 3 dI) b ü 3/ b ü BLJ Ie l i Iop ED sx l r A l A ü ( X https://github.com/y-bar
Data Science API
Engineering Data Science API
Engineering Data Science API Anomaly Detection Time Series Prediction Stats
Test
Engineering Why Data Science API? + . + + •
2 • ( 1 • • 2 • 2 • ( 1 • • 2 • 2 • ( 1 • • 2 I I I ) T I E O . ( T • 2 • ( 1 • I • 2 • ( 1 • I J C D J AB B P S B
Engineering % "$# !
Engineering System API Server (), , Deploy CI
(drone) Format check Unit test FastAPI
Engineering Anomaly Detection API Server
Engineering KPI Prediction API Server
API l Ø P P P I
Ø Ø A
I API K P I A Summary and Prospects
!