circle.png
 

I'm passionate about using data to improve our lives and our society through learning. I recently completed dual masters degrees in Applied Statistics and Information Science at the University of Michigan. I work with Christopher Brooks in the Educational Technology Collective (etc), where we research both methodology and applications of data-driven methods for supporting large-scale learning in digital (MOOCs) and residential (on-campus) learning environments. My thesis research is focused on methods and tools for constructing predictive models in MOOCs, using Bayesian hierarchical modeling to support inference about the full feature extraction, model-building, and hyperparameter tuning pipeline in large-scale machine learning experiments. I am also a developer of the MOOC Replication Framework (MORF), an open source machine learning research framework in collaboration with Ryan Baker at the University of Pennsylvania. 

Bio:

After graduating from the University of Michigan with a Philosophy degree, I worked as an educator and technologist serving students in public urban schools for five years, working with Teach For America - Miami-Dade and KIPP New Orleans Schools. I also served as an Operations Director at the Teach For America New York City Institute in 2011 and 2014, and worked as a Teacher Development Coach with TeachNOLA in 2013. Eager to utilize data science to expand the impact of my work, I returned to the University of Michigan and recently completed dual masters degrees in Applied Statistics and Information Science. I will be entering the PhD program at the University of Washington's Paul G. Allen School of Computer Science and Engineering in fall 2018.

I previously worked as a Professional Practice Fellow in the data science and digital insights team at ProQuest, and as a data science engineering and visualization intern at GoPro. In the winter of 2017, I was a Graduate Student Instructor for SI618: Data Manipulation and Exploratory Data Analysis with Ceren Budak. In the summer of 2017, I was an educational data mining research intern with Ryan Baker at the Penn Center for Learning Analytics, where I developed the computational framework and API for the MOOC Replication Framework, and the auctestr package for R, in collaboration with a research team at Penn and Michigan. I am also a Team Captain and Project Mentor with the Michigan Data Science Team.

In addition to my research, I'm passionate about running, and am a five-time Boston Marathon finisher.

News:

  • 4/2018: I received the University of Michigan School of Information's Margaret Mann Award.
  • 4/2018: I graduated from the University of Michigan with dual master's degrees in Applied Statistics and Information Science.
  • 4/2018: Paper with Chris Brooks and Kaifeng Chen on How Gender Cues in Educational Video Impact Participation and Retention has been accepted as a crossover paper to be presented at the joint "Festival of Learning" co-hosted at the International Conference of Artificial Intelligence in Education (AIED),  International Conference on the Learning Sciences (ICLS), and International Conference on Learning at Scale (L@S).
  • 4/2018: Paper on Student Success Prediction in MOOCs with Chris Brooks has been accepted to User Modeling and User-Adapted Interaction.
  • 1/2018: I will be presenting our work on MOOC Dropout Model Evaluation at the EAAI-18 Symposium at the Association for the Advancement of Artificial Intelligence (AAAI) in New Orleans on 2/4/2018. Conference Agenda.
  • 1/2018: We are excited to announce the alpha release of the MOOC Replication Framework (MORF) Platform! A preprint of the MORF software architecture paper is now available on arXiv.
  • 1/2018: The MORF API is now available on the Python Package Index. PyPi
  • 11/2017: Paper on Network-Augmented Classification in University Coenrollment Networks with Chris Brooks was accepted to LAK18.
  • 11/2017: Paper on MOOC Dropout Model Evaluation with Chris Brooks was accepted to EAAI-2018.
  • 11/2017:  My auctestr package is now officially available on CRAN. (The beautiful hex logo is only on Github)
  • 9/2017: I will be presenting our work Driving with Data: Modeling and Forecasting Vehicle Fleet Maintenance in Detroit with members of the Michigan Data Science Team at Bloomberg Data for Good Exchange in New York City.

Media: