Company

Netflix

30 cases from Netflix (Media streaming, Fintech, Gaming), each digested from a public talk or engineering post and linked to the original. 7 were checked in an online A/B test; 10 report results in production.

Tasks: Evaluate models, Measure impact without an A/B test, Recommend from what the user just did, Avoid false wins in A/B tests, Build a data platform and 19 more. Methods: Sequential recommendation, LLM-as-a-judge, A/B test, Embedding similarity matching, Supervised fine-tuning, Reward model and 73 more. Tools: Elasticsearch, XGBoost, CLIP, vLLM, EconML, Claude and 7 more.

Tech blog: netflixtechblog.com

Fact-Checking at Scale: Building a More Accurate and Efficient Synopsis Factuality Systemmedia-streaming2026-11
Measuring the Impact of Personalized Recommendationsmedia-streaming2026-10
DataJunction as Netflix’s answer to the missing piece of the modern data stackmedia-streaming2026-10
The Lifecycle of LLM-as-a-Judge: Building, Aligning, and Monitoring at scalemedia-streaming2026-09
MAPS: Netflix’s Multimodal Asset Personalization at Scalemedia-streaming2026-08
GenRec: Towards LLM-Native Recommendation at Netflixmedia-streaming2026-07
GenPage: Towards End-to-End Generative Homepage Construction at Netflixmedia-streaming2026-07
Predicting Risk in Content Launches: How Data-Driven Insights can Transform Launch Planningmedia-streaming2026-06
A Human-Augmenting Agentic Workflow for Causal Inferencemedia-streaming2026-06
Thinking Fast & Slow for a Personalized Notification Systemmedia-streaming2026-06
Evaluating Netflix Show Synopses with LLM-as-a-Judgemedia-streaming2026-04
Synchronizing the Senses: Powering Multimodal Intelligence for Video Searchmedia-streaming2026-04
The AI Evolution of Graph Search at Netflixmedia-streaming2026-01
Integrating Netflix’s Foundation Model into Personalization applicationsmedia-streaming2025-11
Post-Training Generative Recommenders with Advantage-Weighted Supervised Finetuningmedia-streaming2025-10
ML Observability: Bringing Transparency to Payments and Beyondmedia-streaming2025-08
FM-Intent: Predicting User Session Intent with Hierarchical Multi-Task Learningmedia-streaming2025-05
Foundation Model for Personalized Recommendationmedia-streaming2025-03
Part 2: A Survey of Analytics Engineering Work at Netflixmedia-streaming2025-01
Recommending for Long-Term Member Satisfaction at Netflixmedia-streaming2024-08
Improve Your Next Experiment by Learning Better Proxy Metrics From Past Experimentsmedia-streaming2024-08
Sequential A/B Testing Keeps the World Streaming Netflix. Part 1: Continuous Datamedia-streaming2024-03
Sequential A/B Testing Keeps the World Streaming Netflix Part 2: Counting Processesmedia-streaming2024-03
Building In-Video Searchmedia-streaming2023-11
Discovering Creative Insights in Promotional Artworkmedia-streaming2023-01
Causal Machine Learning for Creative Insightsmedia-streaming2023-01
Machine Learning for Fraud Detection in Streaming Servicesmedia-streaming2022-09
Reinforcement Learning for Budget Constrained Recommendationsmedia-streaming2022-08
Formulating ‘Out of Memory Kill’ Prediction on the Netflix App as a Machine Learning Problemmedia-streaming2022-07
Experimentation is a major focus of Data Science across Netflixmedia-streaming2022-01