Large scale predictive process mining and analytics of university degree course data

Jurgen Schulte, Pedro Fernandez De Mendonca, Roberto Martinez-Maldonado, Simon Buckingham Shum

Research output: Chapter in Book/Report/Conference proceedingConference PaperOtherpeer-review

4 Citations (Scopus)

Abstract

For students, in particular freshmen, the degree pathway from semester to semester is not that transparent, although students have a reasonable idea what courses are expected to be taken each semester. An often-pondered question by students is: "what can I expect in the next semester?" More precisely, given the commitment and engagement I presented in this particular course and the respective performance I achieved, can I expect a similar outcome in the next semester in the particular course I selected? Are the demands and expectations in this course much higher so that I need to adjust my commitment and engagement and overall workload if I expect a similar outcome? Is it better to drop a course to manage expectations rather than to (predictably) fail, and perhaps have to leave the degree altogether? Degree and course advisors and student support units find it challenging to provide evidence based advise to students. This paper presents research into educational process mining and student data analytics in a whole university scale approach with the aim of providing insight into the degree pathway questions raised above. The beta-version of our course level degree pathway tool has been used to shed light for university staff and students alike into our university's 1,300 degrees and associated 6 million course enrolments over the past 20 years.

Original languageEnglish
Title of host publicationLAK’17 Conference Proceedings
EditorsInge Molenaar, Xavier Ochoa, Shane Dawson
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Pages538-539
Number of pages2
ISBN (Electronic)9781450348706
DOIs
Publication statusPublished - 2017
Externally publishedYes
EventInternational Learning Analytics & Knowledge Conference 2017 - Morris J Wosk Centre for Dialogue, Simon Fraser University, Vancouver, Canada
Duration: 13 Mar 201717 Mar 2017
Conference number: 7th
http://lak17.solaresearch.org/

Conference

ConferenceInternational Learning Analytics & Knowledge Conference 2017
Abbreviated titleLAK 2017
CountryCanada
CityVancouver
Period13/03/1717/03/17
Internet address

Keywords

  • Educational data mining, educational process visualization
  • Learning analytics
  • Predictive modeling
  • Process mining

Cite this