Method

Word2Vec

Skip-gram and CBOW word vectors.

14 cases from 12 companies apply Word2Vec. 4 were checked in an online A/B test; 3 report results in production.

Typical tasks: Retrieve and rank from millions of items, Rank search results, Learn user and item embeddings, Recommend to new users and new items and 5 more. Companies: VK, Airbnb, Expedia Group, VTB, Meta, Samokat.tech and 6 more. Often combined with: Gradient boosting, Named entity recognition, Embedding similarity matching, A/B test, ALS and 45 more.