Massive online open course teaches machine learning and data mining for education research

Guest post by Ryan Baker, Associate Professor in the Graduate School of Education at the University of Pennsylvania.

The Northeast Big Data for Education Spoke has conducted considerable outreach on methods for data science for educational data sets. Workshops have been conducted in New York City, Buffalo, Philadelphia, Pittsburgh, and Boston and include both tutorials by senior researchers and research collaboration generation sessions. In addition, the spoke has supported the ongoing run of the Massive Online Open Course “Big Data and Education” (BDEMOOC), which has had well over 100,000 learners in its several iterations. BDEMOOC helps learners develop skills both in using standard machine learning and data mining algorithms and in working in areas more specific to education such as latent knowledge estimation. BDEMOOC also innovates in using intelligent tutor pedagogy for assignments. Work by Elle Wang establishes that students who took BDEMOOC were likely to go on to submit scientific papers in the area. Data from BDEMOOC has also been used in over twenty scientific papers, many of them first-authored by graduate students. If you would like to collaborate on analyses of BDEMOOC data, please contact Ryan Baker at

Learn more about the Education and Data Literacy Focus Area and the Big Data for Education Spoke.