Presented By O’Reilly and Cloudera
Make Data Work
September 11, 2018: Training & Tutorials
September 12–13, 2018: Keynotes & Sessions
New York, NY

Assumptions, constraints, and risks: How the wrong assumptions can jeopardize any model (sponsored by IBM)

Jennifer Shin (8 Path Solutions | NYU Stern | IBM)
11:20am–12:00pm Thursday, 09/13/2018
Location: 1A 01/02

What you'll learn

  • Understand how assumptions fit into the creation of a statistical model


Common wisdom dictates that we should never make assumptions, lest we be led astray on a false or tangential path of reasoning. However, assumptions are essential when analyzing data in the creation of statistical models. In statistics, assumptions form the foundation of every model we use, and understanding these assumptions is critical to correctly applying the models we create. Applying a model to data where a set of given assumptions does not apply can introduce unexpected errors, which can derail any data-driven strategy.

Using industry examples, Jennifer Shin explores how assumptions fit into the creation of a statistical model, the pitfalls of applying a model to data without taking the underlying assumptions into account, and how to identify datasets where the model and its assumptions are applicable.

This session is sponsored by IBM.

Photo of Jennifer Shin

Jennifer Shin

8 Path Solutions | NYU Stern | IBM

Jennifer Shin is the founder of data science, analytics, and technology company 8 Path Solutions and an adjunct professor at New York University’s Stern School of Business. An experienced data scientist and management consultant, Jennifer has led complex, large-scale, and high-profile projects as a product director at NBCUniversal, director of data science at Comcast, senior principal data scientist at The Nielsen Company, and management consultant at GE Capital, the Carlyle Group, Fortress Investment Group, the City of New York, and Columbia University. Previously, Jennifer taught courses in statistics, data science, and business at UC Berkeley, the Columbia Business School, and the City University of New York. She is internationally recognized as a thought leader, influencer, and expert in data science, business, and technology by governments, corporations, and academic institutions. Jennifer has several patents and trademarks related to data science, machine learning, and AI, has published research in peer-reviewed journals, and has been featured in news publications, press conferences, and on billboards in Times Square and the Vegas Strip. She serves on the data science committee for the Grace Hopper Conference, the advisory board for the data science graduate program at City University of New York, and the advisory board for up-and-coming startups. Jennifer holds an undergraduate degree in economics, mathematics, and creative writing and a graduate degree in statistics, both from Columbia University.