Before the Model: How Machine Learning Products Start...
summary
Describes how Airbnb turns vague ideas into deployed ML products by sizing impact, choosing a business metric, and reformulating problems — e.g., a six‑month project flips a price-prediction model into a booking probability model that suggests daily prices, grows into a 15‑person team, and improves host revenue; a business‑travel classifier uses 1% labeled traffic and a simple logistic regression with high accuracy; platform work adds TensorFlow support and a pipeline to pursue 65 new product ideas.
AI-written summary · about
chapters (7)
- 0:00Introduction to Airbnb ML
- 1:36ML Product Lifecycle
- 3:47Case Study: Smart Pricing
- 8:07Refining Pricing Strategy
- 12:22Search Ranking Optimization
- 14:57Targeting Business Travel
- 18:09Infrastructure and Conclusion
related talks
39mDeveloping Machine Learning for Impact
26mSmall teams, big dreams: How you can get started with AI today
17mLaying the foundation for deep learning
24mChallenges in building Machine Learning models in production
30mDriving a Higher Level of Customer Support with Machine Learning
27mA Look Inside Applied Machine Learning
49mThe Impact of Machine Learning in Companies
46mDeveloping Machine Learning Algorithms in LUN Projects