Welcome (original) (raw)
Sean J. Taylor
Hi!
I am a data scientist, social scientist, statistician, and software developer. I mostly specialize in methods for solving causal inference and business decision problems, and I am particularly interested in building tools for practitioners working on real-world problems. I’m a generalist, I like to hang out with people from many fields and borrow as many ideas as possible. I have collaborated with computer scientists, economists, political scientists, statisticians, machine learning researchers, and business school scholars. It’s fun for me to jump around a bit, continue learning new things, and make connections between fields.
Here are some useful links:
- Motif Analytics (my startup)
- Sign up for my newsletter
- Github
- Google Scholar
- My infrequently updated blog
Background
- [2022-Present] I’m a co-founder and chief scientist at Motif Analytics Read more here!
- 2019-2022 I was a data scientist and manager on the Rideshare Labs team at Lyft.
- 2012-2019, I was a research scientist and manager on Facebook’s Core Data Science Team.
- 2008-2013, I was a Ph.D. student at NYU’s Stern School of Business, concentrating in Information Systems. My dissertation was titled Social Influence from Online Social Signals. My advisor was Sinan Aral.
- 2006-2008, I was a software engineer at Matrix Group, International.
- 2004-2006, I was a research assistant at the Federal Reserve Board.
- 2000-2004, I was an undergraduate at The University of Pennsylvania. I studied Economics, Finance, and Information Systems.
- I grew up in Philadelphia and I’m a huge Eagles fan.
Videos and Podcasts
- What’s New in Data? podcast with John Kutay.
- When not to use SQL a talk at NormConf.
- Minimum Viable Experimentation on the Analytics Engineering Podcast
- Causal Inference and Sequence Data on the Super Data Science podcast.
- The Relationship between Experimentation and Causal Inference talk at the Nubank Data Science meetup.
- Causal Inference Approach to Matching in Two-Sided Marketplaces.
- Interview on The Data Exchange Podcast with Ben Lorica and Jenn Webb.
- When do we actually need Causal Inference talk at the New York Open Statistical Programming Meetup.
- TWIML Interview on Causal Models in Practice with Sam Charrington.
- Interview on the Gradient Dissent Podcast with Lukas Biewald.
- Learning Bayesian Statistics Podcast episode with Alex Andorra.
- My Keynote entitled “In Defense of Curve Fitting” at the 2020 Causal Data Science Meeting
- A short talk about Prophet
- Another talk about Prophet at StanCon, with my friend Ben Letham.
- Interview on the Casual Inference Podcast
- Appearance on Not So Standard Deviations with my friends Hilary Parker and Roger Peng.
- A short interview about exploratory data analysis
- Podcast about my Science paper with my friends John Myles White and Hilary Mason.
- Finding Nate Silver, an Ignite talk about a prediction market I co-developed.
Data Science
Here are some data science posts I’ve written:
- A Personal Retrospective on Prophet
- Bringing more causality to data science
- Locally Optimal
- Designing and Evaluating Metrics
- The Personality Space of Cartoon Characters
- NFL Fans on Facebook
- Debunking Princeton
- The Statistics Software Signal
- Real scientists make their own data
Here are some of my social science papers. Almost all papers are field experiments on online social platforms.
- Displaying things in common to encourage friendship formation: A large randomized field experiment (Quantitative Marketing and Economics) (pdf of conference version)
- Characterizing online public discussions through patterns of participant interactions (CSCW 2018)
- Social Influence Bias: A Randomized Experiment (Science)
- Discussion quality diffuses in the digital public square (WWW 2017)
- Selection Effects in Online Sharing: Consequences for Peer Adoption (EC 2013)
Experimentation and Statistics
Here are some of my papers on experimentation and statistics. I’m relatively new to this field and mostly a consumer of statistics research, rather than a producer.
- Variance-Weighted Estimators to Improve Sensitivity in Online Experiments (EC 2020) (pdf). You can watch a presentation by my co-author Kevin Liou.
- Randomized experiments to detect and estimate social influence in networks (Complex Spreading Phenomena in Social Systems). This is a book chapter with my friend Dean Eckles.
- Active Matrix Factorization for Surveys (Annals of Applied Statistics)
- Forecasting at Scale (The American Statistician) (pdf)
Forecasting Software
- Prophet is an open source forecasting package available in R and Python. You can watch my talk about Prophet. You can also read my explainer thread.