Voting period for this idea type has passed

How AI Improves Dropout Early Warning

To help alert their overworked staff to students in need of attention, a state education agency funded development of an advanced Dropout Early Warning system. In this case study, we discuss our experience integrating machine learning with counseling, social work, and other student services workflows, focusing on predictive quality, personalization, actionability, and scaling up.

Learning Objectives

  1. The importance of actionability and personalization of risk-related information in supporting dropout interventions
  2. How to evaluate the predictive quality of an early warning system
  3. Issues to consider when scaling out an early warning system for millions of students



Daniel Jarratt, Data scientist, Infinite Campus

Add Comments

comments powered by Disqus

SXSW reserves the right to restrict access to or availability of comments related to PanelPicker proposals that it considers objectionable.

Show me another