What Topics and Specialties Does Sean J. Taylor Cover on His Site?

Sean J. Taylor's site presents him as a data scientist, social scientist, statistician, and software developer whose main specialty is methods for causal inference and business decision problems. His stated focus is building tools for practitioners working on real-world problems, and the site organizes his work under four headings: Background, Videos and Podcasts, Data Science, Social Science, and Experimentation and Statistics. The page is a personal professional homepage, not a course or product site, so the topics below describe his areas of work and public talks rather than a structured curriculum.

The core specialty: causal inference for business decisions

The clearest statement of his focus is that he specializes in methods for solving causal inference and business decision problems. This is the thread that connects the rest of the site:

• Causal inference appears repeatedly in his talks and podcasts, including "When do we actually need Causal Inference," "The Relationship between Experimentation and Causal Inference," and "Causal Inference Approach to Matching in Two-Sided Marketplaces."
• Experimentation and statistics is a dedicated section, with talks such as "Minimum Viable Experimentation" and "What's New in Data?"
• Practitioner tooling is an explicit interest: he says he is particularly interested in building tools for people working on real-world problems.

If you are looking for material on how to reason about cause and effect in a business setting, or how experimentation and causal methods relate, those linked talks are the most direct entry points on the site.

Data science and social science

He describes himself as a generalist who collaborates across computer science, economics, political science, statistics, machine learning, and business scholarship. The site reflects this in two ways:

• Data Science and Social Science are separate headings, signaling that he treats them as distinct areas of coverage rather than one blended category.
• His academic background is in social science methods: a Ph.D. at NYU's Stern School of Business in Information Systems, with a dissertation titled Social Influence from Online Social Signals, advised by Sinan Aral.

For readers interested in the social-science side, the dissertation topic and the social science heading are the relevant pointers; for the data-science side, the podcast and talk list covers applied topics.

Background and where the work has been applied

The Background section gives the professional context behind these specialties:

This table is useful if you want to judge whether his methods content comes from an academic, industry research, or startup perspective — the answer is all three, in sequence.

Videos and podcasts: what you can actually watch or listen to

The site's most concrete resource is a list of external talks and interviews. Notable items include:

• "When not to use SQL" — a talk at NormConf, relevant if you work with data querying and want guidance on its limits.
• "Minimum Viable Experimentation" — on the Analytics Engineering Podcast, aimed at practitioners setting up experiments.
• "In Defense of Curve Fitting" — his keynote at the 2020 Causal Data Science Meeting.
• "Causal Models in Practice" — TWIML interview with Sam Charrington.
• Interviews on the Gradient Dissent, Learning Bayesian Statistics, Data Exchange, and Super Data Science podcasts.

The page lists these as links to external platforms; it does not host the media itself, so availability depends on those third-party sites.

How to use the site

The homepage also links to his Twitter, newsletter signup, GitHub, LinkedIn, Google Scholar, and an infrequently updated blog. For someone researching his work, Google Scholar and GitHub are the practical places to go for publications and code; the newsletter is the way to follow new material. The site itself functions as a hub of links rather than a repository of original long-form content.