The study also demonstrates the valuable role of learning data interoperability, supported in this study by IMS Caliper Analytics, a standard format for analytics created to allow a variety of learning tools to return data that can be analyzed in aggregate.
By combining activity data from multiple digital learning tools, it becomes possible to create earlier and more accurate predictions of student achievement. In the hands of professional advisers, this could mean more timely interventions and more students remaining on track for on-time graduation.
“To my knowledge, this project represents one of the few empirical studies to look at student success through combined, digital tool usage data,” says John Fritz, UMBC’s associate vice president for instructional technology. “In addition, the IMS Caliper Analytics standard made it technically possible for a university and two ed-tech companies to pursue shared interests, which is rare in its own right. We learned a lot and appreciated the collaboration very much.”
“We believe that putting actionable data in educators’ hands will have a meaningful impact on student outcomes and retention,” says Dr. Michael Hale, vice president of education at VitalSource.
Overall, the study found 5 major results:
1. Early activity is a strong predictor of passing a class
2. Activity patterns differ from course to course; for instance, a math course features more consistent activity throughout the analyzed term, while a physics course featured three periods of intense activity with lighter activity in between
3. Learning data is a more powerful predictor of student achievement than demography or educational background
4. Combining learning data from multiple sources improves prediction accuracy
5. Students who actively use multiple online resources are more likely to pass a class