ML Engineer · Data Scientist · Applied systems builder
I build ML and analytics products that are meant to ship, be measured, and actually help someone make a decision.
My work usually sits at the intersection of:
- applied ML and forecasting
- evaluation, calibration, and backtesting
- FastAPI, Python, SQL, and TypeScript
- CLI tools, dashboards, and product-style workflows
I care about systems that are inspectable, reusable, and honest about what they do and do not know.
Sports betting product with ML predictions, Kelly-based bet sizing, live odds, and a real deployed surface.
Portfolio site at ianalloway.xyz — project showcase, toolkit index, testimonials, and live Substack RSS.
Applied modeling repo for NBA and NFL edge detection using logistic regression, XGBoost, and ensemble methods.
Reusable ratings and win-probability library with Kelly helpers.
TypeScript package for Kelly sizing, odds conversion, and bankroll math.
R utility toolkit for AI and sports analytics workflows.
Frozen copies of retired public repos, one branch per project.
- products that combine modeling with real user workflows
- cleaner evaluation and decision tooling
- durable portfolio pieces instead of throwaway demos
- B.S. Information Science, University of South Florida
- M.S. Artificial Intelligence, University of South Florida (in progress)
- Interested in ML Engineer, Data Scientist, AI Engineer, and applied research roles
I write about ML systems and applied AI on Alloway AI.