Method
LSTM
Gated recurrent network for sequences.
12 cases from 6 companies apply LSTM. 1 was checked in an online A/B test; 3 report results in production.
Typical tasks: Rank search results, Forecast demand and load, Reduce ML cost, Detect anomalies and 1 more. Companies: Alfa-Bank, Lyft, Samokat.tech, VTB and 2 more. Often combined with: Gradient boosting, Overlap annotation, TF-IDF, Autoencoder anomaly detection, A/B test and 43 more.
Virtual Flow Metering: Forecasting Oil Production with Machine Learning![]() | ![]() | manufacturing | 2025-05 |
| Real-Time Spatial Temporal Forecasting @ Lyft | mobility | 2025-05 | |
| ML in Predicting ESP Failures | — | manufacturing | 2024-05 |
Analyzing Experiment Design Validity in ECG Diagnosis with Machine Learning![]() | ![]() | healthtech | 2024-05 |
| ML for Brain Physiology | — | healthtech | 2023-10 |
| NLP at Alfa-Bank, Part 4: The Development History of a Chatbot | banking | 2023-05 | |
| NLP at Alfa-Bank, Part 7: Analyzing Customer Feedback | banking | 2023-05 | |
NER for Marketplace Search Queries![]() | ![]() | marketplace | 2023-05 |
| Development History of Voice Bot: Legacy Voice Bot of Alfa-Bank and Transition to Modern Methods | banking | 2023-05 | |
| NLP at Alfa-Bank, Part 8: The Development History of an Operator Assistant | banking | 2023-05 | |
| Using phone calls in banking tasks: the debt collection case | banking | 2022-06 | |
| Neural network models on OFD receipt sequences | banking | 2022-06 |


