Online Program Home
My Program

Abstract Details

Activity Number: 660 - Machine Learning: Advances and Applications
Type: Contributed
Date/Time: Thursday, August 1, 2019 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistical Learning and Data Science
Abstract #304953
Title: Beyond Test Scores: Scaling Item Response Theory Modeling for Large-Volume Machine-Learning Applications
Author(s): Lauren Harrell*
Companies: Google
Keywords: item response theory; machine learning; latent variable models
Abstract:

Item Response Theory (IRT) models are traditionally used in educational and psychological measurement contexts where the item parameters are estimated from a sample of data and applied to score participant responses. We discuss how this modeling framework can be applied to extremely large volumes of data and real-time decision making as a parametric machine-learning approach. We highlight some of the challenges and potential workarounds when data volumes exceed millions, if not billions, of cases.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program