Churn Signals
A gradient-boosted churn model with SHAP-based explanations, served behind a small FastAPI service and monitored for drift.
- Python
- XGBoost
- SHAP
- FastAPI
Data Scientist
I build models that turn messy data into decisions worth trusting.
I work across machine learning, statistics, and the messy middle where they meet the real world. This is where I keep my projects, technical notes, and the occasional essay.
01 — Selected work
All projectsProjects
Semantic Paper Search
Retrieval-augmented search over a personal library of ML papers — sentence-transformer embeddings, FAISS index, and a re-ranking step.
- PyTorch
- FAISS
- Transformers
- Next.js
Forecast Kit
A small toolkit for probabilistic time-series forecasting with backtesting, prediction intervals, and clean diagnostic plots.
- Python
- statsmodels
- Polars
02 — Writing
All notesNotes & posts
/Post
Reading Papers Without Drowning
A three-pass system for keeping up with machine learning research without letting the backlog win.
- research
- workflow
- reading
/Note
The Geometry of Gradient Descent
Why the negative gradient is the direction of steepest descent — and what the learning rate is really controlling.
- optimization
- calculus
- machine-learning