Personal data product
NCAA 2026 Bracket Model
I built an interactive bracket model from public basketball data, evaluated MLX models, a production ensemble, and 10,000 Monte Carlo simulations.
- Source data
- Matchup features
- Model ensemble
- Simulation + UI
Interactive product
Explore the full model room.
Test bracket paths, title odds, upset scenarios, model notes, and all 68 teams in the complete data product.
Open full interactive model
Problem
What needed to change
I wanted a practical office-pool decision tool that went beyond gut picks by combining public basketball data, modeling, simulation, and a readable product interface.
Users
Who the system serves
Bracket-pool participants and people reviewing the model, simulation, and interface.
Team context
Where I fit
Independent builder
Independent build with end-to-end ownership from source collection and cleanup through modeling, simulation, and the interactive interface.
Important technical decision
The implementation choice
Compare model approaches, use an ensemble for production picks, and expose confidence and bracket paths instead of a bare prediction list.
Tradeoff or limitation
Where the boundary sits
Validation accuracy and simulation output support comparison; they do not guarantee tournament outcomes.
Implementation
What I personally owned
- Owned the full workflow from data sourcing and cleanup through modeling, simulation, evaluation, and UI packaging.
- Built the static interactive interface around the model outputs rather than leaving them in notebooks.
Result
Result and limitations
- Office-pool decision tool and playful portfolio UI.
- 10,000 Monte Carlo simulations.
- Bracket paths, title odds, upset boards, model notes, and team search.
- The shipped lab makes the model inputs, evaluation result, simulations, bracket paths, and confidence outputs visible in one interface.
Technical scope