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
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
ameliajtaylor
June 28, 2016
Technology
4.9k
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
AJT_Insight_Demo.pdf
Demo completed as an Insight Data Science Fellow.
ameliajtaylor
June 28, 2016
Other Decks in Technology
See All in Technology
もりもり新機能を一挙紹介! AgentCoreに入門して、AWS上にAIエージェントを構築しよう
minorun365
PRO
6
850
製造業のクラウド活用最適解〜AI,DXを加速するデータ基盤の作り方〜
hamadakoji
0
410
noUncheckedIndexedAccess、3時間、1万円。 / noUncheckedIndexedAccess, 3 Hours, 10,000 JPY.
kaonavi
1
330
DevOps Agentで始めるAWS運用 〜フロンティアエージェントが変える運用の現場〜
nyankotaro
1
320
AI活用を推進するために ファインディが下した、一つの小さな決断
starfish719
0
270
実装は速くなった、レビューはどうする? ― 自身のレビューをAIで再現させるサーヴァントエンジニアリングのすゝめ / Implementation got faster. So what about reviews? — An invitation to Servant Engineering: Recreating your own code reviews with AI
nrslib
7
4.2k
OCI Oracle AI Database Services新機能アップデート(2026/03-2026/05)
oracle4engineer
PRO
0
290
ChatworkとBPaaS 異なる特性で学んだAI機能開発の ベストプラクティス
kubell_hr
2
3.1k
サプライチェーンセキュリティの空白地帯 - 信頼できる”依存性”の未来を考える
rung
PRO
2
780
「速く作る」から「正しく作る」へ ─ 生成AI時代の開発フロー改革の ロードマップと実行 ─
starfish719
0
8.7k
非エンジニアがClaudeと挑んだ「1ヶ月間プロダクト30本ノック」
askokc
0
130
Snowflakeと仲良くなる第一歩
coco_se
1
120
Featured
See All Featured
First, design no harm
axbom
PRO
2
1.2k
The Anti-SEO Checklist Checklist. Pubcon Cyber Week
ryanjones
0
160
A Guide to Academic Writing Using Generative AI - A Workshop
ks91
PRO
1
320
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
600
Bridging the Design Gap: How Collaborative Modelling removes blockers to flow between stakeholders and teams @FastFlow conf
baasie
0
580
The Impact of AI in SEO - AI Overviews June 2024 Edition
aleyda
5
1.1k
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
signer
PRO
0
3.6k
Put a Button on it: Removing Barriers to Going Fast.
kastner
60
4.3k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
133
19k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
52
6k
Leveraging LLMs for student feedback in introductory data science courses - posit::conf(2025)
minecr
1
280
<Decoding/> the Language of Devs - We Love SEO 2024
nikkihalliwell
1
240
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