This report presents an educational computing environment for data science education at scale, highlighted in use at the University of California, Berkeley. With the rise of online learners in massively open computing courses (MOOCs), we detail a relevant technical case study of the decisions made in converting an introductory undergraduate data science course into a series of data science edX MOOCs. The focus of this study is on the student and instructor workflow, distributed system infrastructure, cost analysis, cloud resource allocation, and autograding integration in the scaling process. We implement an analytics pipeline for collecting data from Jupyter notebooks and propose a Deep Knowledge Tracing modification to model student progress on coding assignments.
Title
Pedagogy, Infrastructure, and Analytics for Data Science Education at Scale
Published
2018-05-19
Full Collection Name
Electrical Engineering & Computer Sciences Technical Reports
Other Identifiers
EECS-2018-81
Type
Text
Extent
46 p
Archive
The Engineering Library
Usage Statement
Researchers may make free and open use of the UC Berkeley Library’s digitized public domain materials. However, some materials in our online collections may be protected by U.S. copyright law (Title 17, U.S.C.). Use or reproduction of materials protected by copyright beyond that allowed by fair use (Title 17, U.S.C. § 107) requires permission from the copyright owners. The use or reproduction of some materials may also be restricted by terms of University of California gift or purchase agreements, privacy and publicity rights, or trademark law. Responsibility for determining rights status and permissibility of any use or reproduction rests exclusively with the researcher. To learn more or make inquiries, please see our permissions policies (https://www.lib.berkeley.edu/about/permissions-policies).
