Researchers in Spain have developed a predictive modeling system for personalized student dropout rates.
The Dropout Prevention System was trained on data from more than 11,000 students enrolled in online programs at Madrid Open University (UDIMA) over a five-year period.
The system uses machine learning to analyze students' personal, economic, behavioral, and administrative data, as well as academic results and early/late enrollment information.
The system may feed up to 120 factors into a risk profile for each student, represented as an overall percentage.
Susan Therriault, a managing researcher at the American Institutes for Research, cautioned, “One of the things that’s pretty clear is that predictive analytics demonstrates symptoms and not the problems, and you can’t necessary diagnose [those problems] with the symptom information. You usually have to dig deeper.”
From IEEE Spectrum
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found