WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
WeAreDevelopers LIVE • Jun 12, 2020

Anomaly Detection - Using unsupervised Machine Learning for detecting anomalies in customer base

Lukas Kölbl

Faced with scattered, subjective data, an insurer abandoned supervised learning. See how they used robust PCA to build an explainable anomaly detection model that caught 84% of true outliers.

Pause
Mute Enter Fullscreen
#1 about 4 min

Identifying business value through targeted data science

How data scientists bridge the gap between large data pipelines and actionable business insights.

#2 about 2 min

Combining technical skills with strong business communication

Why translating mathematical foundations into understandable language drives successful analytics initiatives.

#3 about 3 min

Balancing model training with data preparation realities

How real-world data science requires significant effort in data cleansing and collaboration rather than just modeling.

#4 about 3 min

Framing the customer anomaly detection use case

Why an insurance company transitioned from manual customer investigations to automated outlier detection.

#5 about 1 min

Ensuring unbiased results and interpretable model explainability

How removing demographic characteristics from algorithms ensures holistic and fair analytical outcomes.

#6 about 3 min

Structuring the machine learning solution approach architecture

Why moving from a supervised to an unsupervised approach successfully mitigates unstructured label data challenges.

#7 about 2 min

Building the analytical record for customer master data

How spending majority project time harmonizing datasets enables high-quality feature engineering and holistic views.

#8 about 2 min

Selecting and iterating on anomaly detection algorithms

Continuous iteration loops with business units help evaluate approaches like isolation forests and autoencoders.

#9 about 3 min

Implementing robust principal component analysis for outliers

Applying modified linear dimensionality reduction techniques effectively separates abnormal behavior from standard peer groups.

#10 about 1 min

Extracting explainability from orthogonal distance metrics

Using reconstruction errors easily identifies which specific feature triggers an outlier classification without complex libraries.

#11 about 2 min

Evaluating production model performance using a confusion matrix

Deploying the automated engine demonstrates high accuracy in classifying standard workflows versus genuine operational outliers.

#12 about 3 min

Measuring business efficiency gains from deployed machine learning

Visualizing peer group behavior clarifies decision boundaries and significantly reduces the manual investigation time previously required.

Matching moments

1:54 min

Evaluating unsupervised anomaly detection model performance in banking

Stefan Donsa Stefan Donsa +1 · LIVE

1:41 min

Implementing semi-automated anomaly detection with human oversight

Katja Träumner

4:45 min

Applying dimensionality reduction for customer profile reconstruction

Stefan Donsa Stefan Donsa +1 · LIVE

2:59 min

Understanding anomaly detection models and reducing false positives

Raz Cohen · LIVE

1:36 min

Performing exploratory data analysis to uncover underlying patterns

Julian Joseph · LIVE

5:21 min

Preventing customer churn with predictive machine learning models

Andreas Christian · LIVE

More from WeAreDevelopers LIVE

WeAreDevelopers LIVE - Is CSS Catching Up to Flash? thumbnail
1:03:33
8 days ago

WeAreDevelopers LIVE - Is CSS Catching Up to Flash?

Chris Heilmann, Daniel Cranney, Bramus Van Damme

WeAreDevelopers LIVE - Project Chopin: Make Your Team and Agents Play Along thumbnail
1:21:17
15 days ago

WeAreDevelopers LIVE - Project Chopin: Make Your Team and Agents Play Along

Chris Heilmann, Daniel Cranney, Krzysztof Cieślak

Fake or News - AI Toothbrushes, Carrier Pigeon Tech & Life on Mars - Krzysztof Cieślak thumbnail
4:23
17 days ago

Fake or News - AI Toothbrushes, Carrier Pigeon Tech & Life on Mars - Krzysztof Cieślak

Chris Heilmann, Daniel Cranney

WeAreDevelopers LIVE - Open Source Agent Toolkits thumbnail
1:00:38
22 days ago

WeAreDevelopers LIVE - Open Source Agent Toolkits

Chris Heilmann, Daniel Cranney, Eddie Jaoude

Fake or News - AI Music Detectors, Translating Ancient Languages & Tiny Heads in Teslas - Eddie Jaoude thumbnail
6:16
24 days ago

Fake or News - AI Music Detectors, Translating Ancient Languages & Tiny Heads in Teslas - Eddie Jaoude

Chris Heilmann, Daniel Cranney

Fake or News: AI Agents Hire Each Other, Spider-Man Ads in Cars & RAM Thieves - Marc Plogas thumbnail
5:46
29 days ago

Fake or News: AI Agents Hire Each Other, Spider-Man Ads in Cars & RAM Thieves - Marc Plogas

Chris Heilmann, Daniel Cranney, Marc Plogas

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 25, 2026 · 16:50–17:20

Stage 7

You Can’t Rerun Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan
Open session

World Congress 2026 North America

September 25, 2026 · 10:20–10:50

Mainstage

How LinkedIn Turns AI Breakthroughs into member and customer value

Erran Berger, Frederic Lardinois

Erran Berger
Frederic Lardinois
Open session

World Congress 2026 North America

September 24, 2026 · 11:40–12:10

Stage 7

Clean Rooms Demystified: Architecture and Patterns for Privacy-Safe Data Collaboration

Anurag Malik

Data Tech Lead @ Intuit

Anurag Malik
Open session

World Congress 2026 North America

September 25, 2026 · 09:00–09:30

Stage 7

AI Agents are Only as Smart as their Context: Building a Real-Time Context Engine

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel
Open session

World Congress 2026 North America

September 24, 2026 · 11:40–12:10

Stage 4

Taming Rogue Agents: Observability-Driven Evaluation for Production Reliability

Anagha Rumade, Anjana Umapathy, Apoorva Jaiswal

Anagha Rumade
Anjana Umapathy
Apoorva Jaiswal
Open session

World Congress 2026 North America

September 24, 2026 · 10:20–10:50

Stage 4

AI Decision Observability: Enabling Transparency and Trust in Intelligent Systems

Amjad Shaikh, Soumil Mandal

Amjad Shaikh
Soumil Mandal

Related videos

Detecting Money Laundering with AI thumbnail
29:37
LIVE • over 5 years ago

Detecting Money Laundering with AI

Stefan Donsa, Lukas Alber

Data Science in Retail thumbnail
58:21
LIVE • over 3 years ago

Data Science in Retail

Julian Joseph

Solving the puzzle: Leveraging machine learning for effective root cause analysis thumbnail
24:31
World Congress 2025 • about 1 year ago

Solving the puzzle: Leveraging machine learning for effective root cause analysis

Bernhard, Varsha Venugopal

Is my AI alive but brain-dead? How monitoring can tell you if your machine learning stack is still performing thumbnail
48:07
LIVE • almost 5 years ago

Is my AI alive but brain-dead? How monitoring can tell you if your machine learning stack is still performing

Lina Weichbrodt

How We Built a Machine Learning-Based Recommendation System (And Survived to Tell the Tale) thumbnail
27:23
World Congress 2023 • almost 3 years ago

How We Built a Machine Learning-Based Recommendation System (And Survived to Tell the Tale)

Dora Petrella

What non-automotive Machine Learning projects can learn from automotive Machine Learning projects thumbnail
48:01
World Congress 2022 • over 4 years ago

What non-automotive Machine Learning projects can learn from automotive Machine Learning projects

Jan Zawadzki

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.