Method
TF-IDF
Term-weighted sparse text representation used for retrieval and classification.
21 cases from 14 companies apply TF-IDF. 2 were checked in an online A/B test; 6 report results in production.
Typical tasks: Learn user and item embeddings, Retrieve and rank from millions of items, Build an assistant over internal docs, Recommend to new users and new items and 9 more. Companies: Alfa-Bank, VK, VTB, Avito, Yandex, Rabota.ru and 8 more. Often combined with: Gradient boosting, Logistic regression, Overlap annotation, Embedding similarity matching, A/B test and 66 more.



