Guest post by Ryan Baker, Associate Professor in the Graduate School of Education at the University of Pennsylvania.
The ASSISTments Longitudinal Data Competition invited data scientists around the world to participate in a competition around the analysis of student data. Data from middle school student use of a popular online learning platform for mathematics was combined with data on whether these middle school students eventually took a job in STEM after attending college. The participants’ task was to predict eventual job from middle school interaction data, involving just under a million software interactions by over a thousand students. Over 200 data scientists worldwide participated in the competition, with first prize going to a large team of researchers and second prize going to an individual graduate student. A workshop to discuss the competition was held during the July 2018 Conference of Educational Data Mining in Buffalo, NY; and a special issue of the Journal of Educational Data Mining will be published in August 2020.