Generalizing predictive models of admission test success based on online interactions Articles uri icon

publication date

  • September 2019

start page

  • 1

end page

  • 19

issue

  • 18

volume

  • 11

abstract

  • To start medical or dentistry studies in Flanders, prospective students need to pass a central admission test. A blended program with four Small Private Online Courses (SPOCs) was designed to support those students. The logs from the platform provide an opportunity to delve into the learners' interactions and to develop predictive models to forecast success in the test. Moreover, the use of different courses allows analyzing how models can generalize across courses. This article has the following objectives: (1) to develop and analyze predictive models to forecast who will pass the admission test, (2) to discover which variables have more effect on success in different courses, (3) to analyze to what extent models can be generalized to other courses and subsequent cohorts, and (4) to discuss the conditions to achieve generalizability. The results show that the average grade in SPOC exercises using only first attempts is the best predictor and that it is possible to transfer predictive models with enough reliability when some context-related conditions are met. The best performance is achieved when transferring within the same cohort to other SPOCs in a similar context. The performance is still acceptable in a consecutive edition of a course. These findings support the sustainability of predictive models.

keywords

  • generalizability; indicators; learners' success; learning analytics; prediction; spocs