MOOC Dropout Prediction Challenge Seminar

Mon, 02/19/2018 - 12:00pm to 1:30pm

North Quad 2435

The AIM Analytics bi-weekly seminar series is hosting collaborative events aimed at explaining data, approaches taken in the field, and technical advice on how the challenge might be approached. The first MOOC Dropout Prediction Challenge seminar will discuss the data, how to access the MOOC Replication Framework (MORF), and demo if time permits.

RSVP using this form

The MOOC Dropout Prediction Challenge is open to all students, staff, or faculty at the University of Michigan. April 23, 2018 deadline. Team with the best model will receive a $500 prize.

The Challenge includes: 

  • Dataset- The University of Michigan collected data from different courses run on the Coursera platform, with real learner interactions. A single course offering will be provided to participants under a data use agreement to allow for exploration of data.
  • Problem Statement- For this task, dropout will be considered as a student who completes the third week of the course but does not show any clickstream activity in the final week. 
  • Evaluation- Models created by participants will be run on the MOOC Replication Framework (MORF), created through a collaboration between the University of Michigan School of Information and the University of Pennsylvania Center for Learning Analytics.

For more information about the MOOC Data Challenge, visit the data challenge page and receive updates using this form.

Academic Innovation at Michigan Analytics workshop series (AIM Analytics) is a bi-weekly seminar series for researchers across UM who are interested in learning analytics. The workshop series is sponsored by Academic Innovation and Rackham Interdisciplinary Workshops.

Invited AIM talks and events for 2018 Winter semester:

  • 1/22 Invited talks: René Kizelcec
  • 2/5 Prediction challenge group meeting
  • 2/19 AI Fellows talk
  • 3/19 Invited talk: Timothy Nokes-Malach
  • 4/2 Prediction challenge group meeting
  • 4/16 Community presentations