Our results highlight several early indicators of student attrition and show that dropout can be accurately predicted even when predictions are based on a single term of academic transcript data. We invite research and practice papers that address the “convergence of communities” in lak and bring a novel perspective and approach for reflecting on the field. We demonstrate how existing mooc dropout prediction pipelines can be made interpretable, all while having predictive performance close to existing techniques. Based on this, we explore the universal feature tables applicable to dropout prediction for university students in any academic year We design several feature tables and compare the performance of six machine learning models on these feature tables. The proceedings of the practitioner track from lak’16 contains 12 short papers that share reports on the piloting and deployment of new and emerging learning analytics tools and initiatives.
WATCH
