Conference, Journal, and Workshop Articles/Posters (Peer-Reviewed)
Josh Gardner and Christopher Brooks. Student Success Prediction in MOOCs. User Modeling and User-Adapted Interaction (UMUAI): The Journal of Personalization Research. In press. PDF.
Christopher Brooks, Josh Gardner, and Kaifeng Chen (2018). How Gender Cues in Educational Video Impact Participation and Retention. To appear in: Proceedings of the 2018 International Conference on the Learning Sciences (ICLS).
Josh Gardner, Christopher Brooks, Juan Miguel Andres, and Ryan Baker. Replicating MOOC Predictive Models at Scale. To appear in: Proceedings of the Fifth Annual Meeting of the ACM Conference on Learning@Scale; June 2018; London, UK.
Josh Gardner and Christopher Brooks. Coenrollment Networks and their Relationship to Grades in Undergraduate Education. Proceedings of the 8th International Conference on Learning Analytics and Knowledge (LAK18); March 5-9, 2018; Sydney, NSW, Australia. PDF. Invited for submission of an extended version to a special issue of the Journal on Learning Analytics.
Josh Gardner and Christopher Brooks. MOOC Dropout Model Evaluation. Eighth AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18); February 3-4, 2018; New Orleans, LA. PDF.
Josh Gardner, Danai Koutra, Jawad Mroueh, Victor Pang, Arya Farahi, Sam Krassenstein, and Jared Webb. Driving with Data: Modeling and Forecasting Vehicle Fleet Maintenance in Detroit. Bloomberg Data For Good Exchange; September 24, 2017; New York, NY. Also appeared in Data Science for Social Good Conference; September 28-29; Chicago, IL. arXiv.
Josh Gardner and Christopher Brooks. Predictive Models with the Coenrollment Graph: Network-Based Grade Prediction in Undergraduate Courses. The Third International Workshop on Graph-Based Educational Data Mining at 10th International Conference on Educational Data Mining; June 2017; Wuhan, CN.
Josh Gardner and Christopher Brooks. Moving MOOC Modeling Forward: A Statistical Framework for Dropout Model Evaluation in MOOCs. The 10th International Conference on Educational Data Mining; June 2017; Wuhan, CN.
Josh Gardner and Christopher Brooks. A Statistical Framework for Predictive Model Evaluation in MOOCs. Fourth Annual Meeting of the ACM Conference on Learning@Scale; April 2017; Cambridge, MA.
Josh Gardner and Christopher Brooks. Statistical Approaches to the Model Comparison Task in Learning Analytics. Workshop on Methodology in Learning Analytics (MLA) at 7th International Conference on Learning Analytics and Knowledge; March 2017; Vancouver, BC.
Gardner, Josh, Ogechi Onuoha, and Christopher Brooks. Integrating Syllabus Data into Student Success Models. 7th International Learning Analytics and Knowledge Conference; March 2017; Vancouver, BC.
In Submission/Under Review
Josh Gardner, Christopher Brooks, Juan Miguel L. Andres, and Ryan Baker. MORF: A Framework for MOOC Predictive Modeling and Replication At Scale. arXiv.
Josh Gardner and Christopher Brooks. Evaluating Predictive Models of Student Success: Closing the Methodological Gap. arXiv.
MORF (MOOC Replication Framework) 2.0: A framework and computational platform for reproducible predictive modeling research in Massive Open Online Courses. Co-Developer (with Juan Miguel Andres of the University of Pennsylvania, Christopher Brooks, and Ryan Baker). Website. Github. PyPi.
Posters, Consulting Reports, and Other Presentations
Spooner, Taylor and Josh Gardner (2017). The eKool Student Information System.
Gardner, Josh, Hongyu (Victor) Pang and Xilin Zhang. Predicting Cost and Duration of Maintenance Jobs in the City of Detroit Vehicle Fleet. Report developed in partnership with the City of Detroit Office of Operations and Infrastructure and the Michigan Data Science Team; April 2016.
Josh Gardner and Christopher Brooks. Good, Better, Best: Frequentist and Bayesian Methods for Statistical Evaluation of Predictive Models and Feature Extraction in MOOCs. Poster Presented at: Michigan Student Symposium for Interdisciplinary Statistical Sciences; March 2017; Ann Arbor, MI.
Gardner, Josh, Jiacheng Shi, and Yichao Yang. Seeing the Forest and the Trees: Building Interpretable Classification Trees for Residential Lead Level Prediction in Flint. Poster Presented at: Michigan Institute for Data Science (MIDAS) Annual Symposium; November 2016; Ann Arbor, MI.
SI618: Data Manipulation and Analysis. Graduate Student Instructor, Winter 2017 (instructor Ceren Budak). Course description.
Michigan Data Science Team 2017-2018 Data Science Tutorial Series. Organizer and Tutorial Presenter. Github.