Search
Program Calendar
Browse By Day
Browse By Time
Browse By Person
Browse By Unit
Browse By Session Type
Search Tips
Annual Meeting Housing and Travel
Personal Schedule
Sign In
X (Twitter)
Machine Learning is quickly becoming more common place in contemporary society. One of the primary barriers to implementing machine learning algorithms in other educational contexts is that data gathered in educational setting is often low dimensional (e.g. it contains few features or variables). This makes training effective machine learning algorithms difficult. This research addresses this concern by evaluating different machine learning algorithms in low dimensional space that are reflective of the possible data points that a school might have available to train an algorithm. Further algorithms are compared across differing sample sizes that are reflective of likely available populations. Implications for practice are discussed.
Jaret Hodges, University of North Texas
Lindsay Ellis Lee, East Tennessee State University
Kendal Smith, University of North Texas