Method
HDBSCAN
Hierarchical density-based clustering with noise points.
9 cases from 8 companies apply HDBSCAN. 1 was checked in an online A/B test; 2 report results in production.
Typical tasks: Learn user and item embeddings, Recommend from what the user just did, Rank search results, Analyze user behavior and 2 more. Companies: VTB, Spotify, MegaFon and 5 more. Often combined with: UMAP, Gradient boosting, k-means, Text clustering, LLM labeling and 37 more.
Unsupervised Topic Discovery with Text Embeddings![]() | ![]() | fintech | 2026-10 |
A Cluster-Based Approach to CTR Forecasting for Millions of Advertised Products![]() | ![]() | marketplace | 2026-05 |
Multimodal Soup: Turning a Heap of Ad Banners into Meaningful Clusters![]() | ![]() | adtech | 2026-05 |
| An Automated Request Handling Service for SMBs | banking | 2026-05 | |
| LLMs and Other NLP Models in the Service of CRM and Customer Journey Improvement | banking | 2025-05 | |
| Recursive Embedding and Clustering | media-streaming | 2023-12 | |
| Through Thorns to Data: Challenges and Successes in Searching and Processing Transactions in FinTech | banking | 2023-10 | |
Modeling the Behavior of an Oil Spill![]() | ![]() | manufacturing | 2023-05 |
Clustering subscriber messages![]() | ![]() | telecom | 2022-06 |




