Amazon Search: The Joy of Ranking Products
summary
Covers the set of relevance algorithms Amazon Search uses today, including a general machine-learning ranking framework applied within categories and methods for blending separate rankings in All Product Search. Describes query-to-product matching techniques and category-specific ranking algorithms developed for books and fashion.
AI-written summary · about
chapters (12)
- 0:00Intro
- 1:12Search Ranking Models
- 2:10Training Labels
- 3:24Mixing Click and Purchase Targets
- 5:22Fast Feature Evaluation
- 10:30Components of the Blending Score
- 11:25All Product Search - Blending
- 12:51Match Set
- 13:51How do non-text matches happen
- 14:55Cold Start
- 20:02Non-Relevance Sort - Improvement
- 20:42Search Relevance Team
related talks
51mHow to Effectively Rank All of Runet's Products
55mImproving product discovery via relevance and ranking optimization
39mRanking Listings with Machine Learning and ElasticSearch
55mLearning to Rank, a Little
40mLevel Up: Everything you need to know about search, ...
38mLearning to Rank: where search meets machine learning #bbuzz
31mEverything in its Right Place: Optimising Ranking in Online Grocery
44mRobust AI Search Ranking for Radical C2C Marketplace Growth