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

Aliens in Quarantine, Python Deprecates Loops, and AI Buys Old Books - Zbyszek Tenerowicz thumbnail
5:43
5 days ago

Aliens in Quarantine, Python Deprecates Loops, and AI Buys Old Books - Zbyszek Tenerowicz

Chris Heilmann, Daniel Cranney

WeAreDevelopers LIVE - Node and Package Security thumbnail
1:08:30
5 days ago

WeAreDevelopers LIVE - Node and Package Security

Chris Heilmann, Daniel Cranney, Zbyszek Tenerowicz

WeAreDevelopers LIVE - Streaming HTML thumbnail
1:10:26
12 days ago

WeAreDevelopers LIVE - Streaming HTML

Chris Heilmann, Daniel Cranney, Jad Joubran

WeAreDevelopers LIVE - CODE100 at WeAreDevelopers Europe thumbnail
1:02:34
19 days ago

WeAreDevelopers LIVE - CODE100 at WeAreDevelopers Europe

Chris Heilmann, Daniel Cranney, Justin Halsall, Werner Jeschko, Nicole Jeschko, Mirco Tomić

WeAreDevelopers LIVE - Web Performance in an AI World thumbnail
1:07:59
26 days ago

WeAreDevelopers LIVE - Web Performance in an AI World

Chris Heilmann, Daniel Cranney

FIFA Hack, Midjourney Does Ultrasounds, and Trampoline Traffic Lights - Nicole Jeschko and Werner Jeschko thumbnail
5:55
about 2 months ago

FIFA Hack, Midjourney Does Ultrasounds, and Trampoline Traffic Lights - Nicole Jeschko and Werner Jeschko

Chris Heilmann, Daniel Cranney

Upcoming sessions on this topic

Open session

World Congress 2026 North America

You Can’t Re-Run 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

AI-Powered Incident Triage: How We Built GenAI Agents with MCPs to Automate On-Call Workflows

Prakshal Doshi

Site Reliability Engineer

Prakshal Doshi
Open session

World Congress 2026 North America

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

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel
Open session

World Congress 2026 North America

AI Decision Observability: Enabling Transparency and Trust in Intelligent Systems

Soumil Mandal, Amjad Shaikh

Soumil Mandal
Amjad Shaikh
Open session

World Congress 2026 North America

Microservice Cognitive Index for Deploy Diagnosis and Change Impact

Sachin Gupta

Member of Technical Staff 2 at eBay

Sachin Gupta
Open session

World Congress 2026 North America

Proactive AI That Doesn’t Annoy Users: Building Context-Aware Notification Systems

Raju Dandigam Dandigam

Engineering Manager at Navan

Raju Dandigam Dandigam

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 • about 3 years ago

Data Science in Retail

Julian Joseph

Solving the puzzle: Leveraging machine learning for effective root cause analysis thumbnail
24:31
WWC 2025 • 12 months 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
WWC 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
WWC 2022 • about 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.