|
|
Developed an incrementality estimation and bidding approach using experimental lift data and an ensemble of conversion models, iteratively validating and tuning via backend tests to achieve a 10X lift in estimated incremental conversions.
2022-2025I conducted surveys and matched to Census data to model demand. I used this in a gravity model to estimate market size of sports betting in states that were considering legalizing.
2018Applied Monte Carlo simulation techniques to estimate aggregate view outcomes for planned video lineups, addressing systematic underprediction caused by outlier effects. The approach enabled reliable percentile-based forecasting, was adopted in a patented solution, and improved planning accuracy for internal stakeholders.
2018-2021Redesigned predictions of hosted players' play to improve transparency and interpretability, achieving more accurate identification of high-value players for ~80% of cases and enabling better rewards allocation.
2016-2018Built a customer lifetime value model of our commerical policy data.
2014-2016Helped refresh our decade-old commercial auto model, combining two previous models.
2014-2016Project Titan is a set of software I wrote to make predictions for sports. This is a large project with web scraping, modeling, and architecture components.
2023-2022Link