Method

Anomaly detection

Detecting unusual points or behavior, streaming or batch.

43 cases from 34 companies apply Anomaly detection. 15 report results in production. Includes variants: Autoencoder anomaly detection, Isolation Forest.

Typical tasks: Detect anomalies, Catch fraud and abuse, Moderate content at scale, Build a data platform and 10 more. Companies: Uber, Pinterest, Lyft, Mercari, Databricks, Meta and 28 more. Often combined with: Isolation Forest, Threshold selection, Autoencoder anomaly detection, Gradient boosting, Data quality checks and 83 more.

Metrics Board: Building an Agent-ready Metrics Layersocial2026-10
Beyond Dashboards: How Grupo Bimbo Delivers Insights with Databricks AgentBricksretail2026-06
Databricks on Databricks: Automating Service Reliability at Scalesaas-b2b2026-06
Method of Automated Construction of Production Digital Twins Using LLM Agentsmanufacturing2026-05
DrP: Meta’s Root Cause Analysis Platform at Scalesocial2025-12
Building an anomaly detection platform at DoorDash to catch fraud trends earlyfood-delivery2025-09
Building Slack’s Anomaly Event Responsesaas-b2b2025-09
Virtual Sensors in Industrymanufacturing2025-05
CyberFarm: How We Teach AI to Monitor Cowsmanufacturing2025-05
A Short-Term Anomaly Forecasting Model for Univariate Time Series and Its Use in the Sfera.IAS Productgeneral2025-05
Virtual Flow Metering: Forecasting Oil Production with Machine Learningmanufacturing2025-05
Anomaly Detection in Time Series Using Statistical Analysistravel2025-04
Using ML to detect and respond to performance degradations in slices of Stripe paymentsfintech2025-01
Experience Building a Data Quality Tool at MTStelecom2024-05
How We Launched a New Promotion Model: Matching and Regional Testsclassifieds2024-05
ML in Predicting ESP Failures—manufacturing2024-05
Anomaly Detection: Anomaly Scoring for Preventive Detection of Information System Failuresbanking2024-05
TSAD: A Python Library for Solving ML Problems in Industrymanufacturing2024-05
How the New York Times Games Data Team Revamped Its Reportinggaming2024-02
Real-world Insights: Anomaly Detection in Internet Traffictravel2024-02
Explaining Autoencoder Anomalies in Industrial Control Systemsmanufacturing2023-10
Risk Entity Watch - Using Anomaly Detection to Fight Fraudmobility2023-09
Graph Usage in Combating ATO Fraud Riskfintech2023-09
Unsupervised graph anomaly detection - Catching new fraudulent behavioursfood-delivery2023-08
New Approaches For Detecting AI-Generated Profile Photossocial2023-06
Diagnosing Oil and Gas Pipelines Using Machine Learning—manufacturing2023-05
Data-Centric AI: A Review of Methodshealthtech2023-05
A Trial ML System Design Interview—retail2023-05
ML System Design Doc Challenge – Finalbanking2023-05
Warden: Real Time Anomaly Detection at Pinterestsocial2023-05
Building a large scale unsupervised model anomaly detection system — Part 2mobility2023-04
Follow the White Rabbit: Finding The Women With The Red Dress In A Torrent of Event Logsmarketplace2023-03
D3: An Automated System to Detect Data Driftsmobility2023-02
What is good for a doctor is death for an engineer: extra requirements for medical AI services—healthtech2022-10
How to understand who is on the network if you can't askmanufacturing2022-10
Using a recommender system to find anomalies in operating system process launchesgeneral2022-10
Machine Learning for Fraud Detection in Streaming Servicesmedia-streaming2022-09
Clustering subscriber messagestelecom2022-06
A small BERT towards Large Medical Modelshealthtech2022-06
Full-Spectrum ML Model Monitoring at Lyftmobility2022-06
Suspecting the Unsuspected. Extracting and Analyzing Log Anomaliesmarketplace2022-05
In-house monitoring of Payments success ratee-commerce2022-02
Project RADAR: Intelligent Early Fraud Detection System with Humans in the Loopmobility2022-02