Forecasting Student Outcomes in Week Two Based on Student Behaviors in Class

Early warning systems often rely on a combination of student background data and outcomes from formative assessment. But it is possible that waiting until after a student does poorly on an exam is too late. This research focuses on exploring whether student behavior data gleaned from the LMS and other classroom digital technology can be used to identify students at risk before the first formative assessment. Results suggest that use of the quantity and quality of student participation can provide reasonable predictive skill of student performance even by the second week of the course.

Outcomes: Learn how various measures of student behavior are related to student exam grades in multiple courses *Learn how measures of student behavior were collected from multiple sources and merged into an anonymous common database *Learn with what accuracy student success can be predicted as a function of weeks in a semester