Method
S-learner
Single model with treatment as a feature.
8 cases from 6 companies apply S-learner. 5 were checked in an online A/B test; 1 report results in production.
Typical tasks: Decide who gets an offer, Optimize decisions, Predict churn and lifetime value, Evaluate models. Companies: VTB, The New York Times, DoorDash, Avito, Spotify and 1 more. Often combined with: Inverse propensity weighting, A/B test, Propensity / response modeling, Uplift evaluation (Qini/AUUC), Holdout / global control group and 24 more.
| Uplift Models in Promotional Offers | banking | 2026-05 | |
| Smarter promotions with causal machine learning | food-delivery | 2025-12 | |
| Scaling Subscriptions at The New York Times with Real-Time Causal Machine Learning | media-streaming | 2025-10 | |
| How We Grew Sales Team Efficiency with Customer Ranking | classifieds | 2025-05 | |
NBA in Cross-Service: Applying ML in Plus Daily![]() | ![]() | media-streaming | 2024-05 |
| Experimenting with Machine Learning to Target In-App Messaging | media-streaming | 2023-06 | |
| How The New York Times Uses Machine Learning To Make Its Paywall Smarter | media-streaming | 2022-08 | |
| From look-alike to uplift in customer lifecycle models | banking | 2022-06 |
