Altametrics
Machine Learning Intern · Costa Mesa, CA
- Built production ML forecasting for daily sales across four national restaurant chains — McDonald's, Taco Bell, Jack in the Box, Chipotle — covering thousands of locations.
- Cut forecast error from 12% to 5%, which translates directly into tighter labor scheduling and lower food cost.
- Led a team of interns on the data pipeline behind the model: scheduled crawlers behind a rotating proxy pool, a headless browser for pages that render client-side, and an ETL layer that lands everything in a cleaned, de-duplicated store.
- Designed the schema and indexes — range partitioning by date and a composite B+ tree — and ordered the feature joins by selectivity to keep them fast.
- Engineered 30+ predictive features from weather, zip-code demographics, holidays, seasonality, school calendars, and national events, plus macroeconomic indicators.
- Worked on the full model lifecycle end to end: preprocessing, feature engineering, walk-forward cross-validation, hyperparameter tuning, and back-testing against historical sales.
- Worked full-time across two consecutive summers — Summer 2025 and Summer 2026 — alongside summer-session coursework (CS 61C in 2025, CS 184 and CS 161 in 2026).
