Paths to Predictive Learning Analytics: Can Data Predict Learner Success?

Thursday, November 01 | 10:45AM–11:30AM MT | Mile High Ballroom 2A/3A, Ballroom Level
Session Type: Breakout Session
Delivery Format: Interactive Presentation
We will describe Indiana University's journey in developing predictive models of learners' interactions with digital learning management environments (LMEs). Through partnerships with leaders in modeling and predicting learner outcomes from LME interactions, we will discuss the lessons learned, the issues encountered, and the relevance of predictive analytics in higher education.

Outcomes: Identify relevant data architectures and pipelines for the development of predictive models * Understand the process of developing and implementing predictive models from digital LMEs and institutional systems * Explore the issues and potential for the application of predictive models in higher education


  • Matthew Gunkel

    Associate Vice Chancellor and CIO, University of California, Riverside
  • Jason Kaetzel

    Principal Solutions Analyst, Indiana University
  • Josh Quick

    Learning Data Analyst, Indiana University

Resources & Downloads

  • The Path to Predictive Learning Analytics Presentation Slides

    Updated on 11/26/2019