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
AJT_Insight_Demo.pdf
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
ameliajtaylor
June 28, 2016
Technology
0
4.6k
AJT_Insight_Demo.pdf
Demo completed as an Insight Data Science Fellow.
ameliajtaylor
June 28, 2016
Tweet
Share
Other Decks in Technology
See All in Technology
AgentCoreとLINEを使った飲食店おすすめアプリを作ってみた
yakumo
2
170
ADK + Gemini Enterprise で 外部 API 連携エージェント作るなら OAuth の仕組みを理解しておこう
kaz1437
0
130
頼れる Agentic AI を支える Datadog のオブザーバビリティ / Powering Reliable Agentic AI with Datadog Observability
aoto
PRO
0
250
ガバメントクラウドにおけるAWSの長期継続割引について
takeda_h
2
5.4k
LINEヤフーにおけるAIOpsの現在地
lycorptech_jp
PRO
5
2k
Phase03_ドキュメント管理
overflowinc
0
1.7k
SaaSに宿る21g
kanyamaguc
2
110
形式手法特論:SMT ソルバで解く認可ポリシの静的解析 #kernelvm / Kernel VM Study Tsukuba No3
ytaka23
1
730
Phase01_AI座学_基礎
overflowinc
0
2.6k
SSoT(Single Source of Truth)で「壊して再生」する設計
kawauso
1
220
Kiro Powers 入門
k_adachi_01
0
140
「お金で解決」が全てではない!大規模WebアプリのCI高速化 #phperkaigi
stefafafan
4
2.2k
Featured
See All Featured
[RailsConf 2023] Rails as a piece of cake
palkan
59
6.4k
ラッコキーワード サービス紹介資料
rakko
1
2.7M
Fashionably flexible responsive web design (full day workshop)
malarkey
408
66k
Claude Code のすすめ
schroneko
67
220k
Done Done
chrislema
186
16k
Site-Speed That Sticks
csswizardry
13
1.1k
GitHub's CSS Performance
jonrohan
1032
470k
Sam Torres - BigQuery for SEOs
techseoconnect
PRO
0
220
sira's awesome portfolio website redesign presentation
elsirapls
0
200
Discover your Explorer Soul
emna__ayadi
2
1.1k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
122
21k
Embracing the Ebb and Flow
colly
88
5k
Transcript
Water they doing with those meters? Amelia Taylor A consulting
project for Valor Water Analytics: Insight Fellow
Utility companies have leaks.
Analytics Companies Have a Problem
Analytics Companies Have a Problem Prototype Model
Analytics Companies Have a Problem Prototype Model Meter Tampering
Scores
Analytics Companies Have a Problem Prototype Model Meter Tampering
Scores New Scores Using new supervised data
Data Existing Model Scores & Labels Algorithms
Data Existing Model Scores & Labels SMOTE Resample
Algorithms
Data Existing Model Scores & Labels SMOTE Resample
Random Forest Classification New Scores Algorithms
Data Existing Model Scores & Labels SMOTE Resample
Random Forest Classification Gradient Descent New Scores Algorithms
Metrics My algorithm: Random Forest with SMOTE
Company Prototype Model ROC Curves Increased AUC by 70%
Metrics My algorithm: Random Forest with SMOTE
Company Prototype Model ROC Curves Increased AUC by 70%
Metrics My algorithm: Random Forest with SMOTE
Company Prototype Model ROC Curves Increased AUC by 70%
Actionable Insights Quickly identified features not performing as expected.
Tampered Untampered
Actionable Insights Quickly identified features not performing as expected.
Tampered Untampered
Actionable Insights Untampered Tampered 99.924% 0.076% Untampered Tampered 50% 50%
Quickly identified features not performing as expected. Before SMOTE After SMOTE Tampered Untampered
Deliverables 1. Python Modules & API
Deliverables 1. Python Modules & API 2. Scalable platform for
improving scores from multiple prototype models.
Deliverables 1. Python Modules & API 2. Scalable platform for
improving scores from multiple prototype models. 3. Improved the true positive rate (recall) balancing that with the false positive rate. AUC Increased 70%
About Me Amelia Taylor Green: Unbiased Squangle PhD Mathematics
University of Kansas