Hello!

Hi, my name is Ege. I’m a Data Scientist based in the San Francisco Bay Area. You can check out my resume and publications, or browse my blog posts on statistics, data science, and physics.

About me

I am a Senior Data Scientist with a background in experimental physics, specializing in causal inference, experimentation, and statistical modeling at scale.

Meta (Jun 2025 – Present)

I work on ads measurement at Meta, where I help advertisers understand the true return on investment of their ad campaigns. My work focuses on building and strengthening attribution strategy by integrating experimentation with causal inference methods (difference-in-differences, propensity score matching, synthetic controls, and incrementality frameworks) to better reflect how the advertising industry measures impact. I also lead cross-functional efforts to standardize fair-credit rules for external measurement partners across methodologies like multi-touch attribution (MTA), media mix modeling (MMM), and geo-based lift studies (GeoLift). This work has had a 0.1% incremental revenue impact, translating to roughly $160M per year.

Happy Returns (PayPal / UPS) (May 2022 – May 2025)

Before Meta, I spent three years at Happy Returns, a retail returns platform that was acquired by PayPal and later UPS during my time there. I started out building predictive models to forecast shipping supply needs across thousands of locations and creating dashboards that teams across the company ended up relying on. Over time my work shifted toward experimentation and optimization. I led multi-round A/B tests on customer-facing features and built time-series forecasting pipelines to optimize shipping logistics across 10,000 centers. It was a good environment to develop a broad set of skills quickly, and I got to see the company through its acquisition by UPS while my role kept growing.

Graduate Research, NYU (Sep 2016 – May 2022)

My PhD research at the Center for Quantum Phenomena at New York University focused on current-induced spin dynamics in antiferromagnetic materials, supervised by Andy Kent. I worked with hundreds of gigabytes of image data from electron microscopy experiments and developed analytical and numerical models to extract signal from high-dimensional voltage data as a function of temperature, current, and magnetic field.

I write about topics I find interesting in the posts section, mostly statistics, probability, and the occasional physics simulation.

Below is an interactive Ising model simulation from an upcoming blog post.
(Press play to restart!)