You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Production-grade causal uplift modeling on 14M rows, benchmarks S-Learner, T-Learner, and FT-Transformer challengers on the Criteo dataset, with Optuna tuning, MLflow tracking, FastAPI + Docker + Google Cloud Run serving, and a Streamlit dashboard.
Uplift modeling / causal marketing on a 64,000-customer randomized email trial: who visits BECAUSE of the email, not just who visits. S-/T-Learner + class-transformation models evaluated by Qini/AUUC; targeting the top uplift decile cuts ~30% of sends. Live interactive dashboard.