Andrew Lan

Interests

Personalized education, convex optimization, probabilistic models, machine learning, signal processing.

Research

Andrew's research focuses on the development of human-in-the-loop machine learning methods to enable scalable, effective, and fail-safe personalized learning in education, by collecting and analyzing massive and multi-modal learner and content data. This massive and multi-modal learner and content data can be collected in both traditional classrooms and online learning platforms, e.g., during massive open online courses (MOOCs). His vision is to develop a system that delivers high-quality, affordable, and personalized learning experiences to every learner in the world. He is also broadly interested in areas including convex optimization, probabilistic models, machine learning, and signal processing. 

Biography

Prior to joining UMass, Andrew was a postdoctoral research associate in the EDGE Lab, Princeton University, from 2017 to 2018. Andrew was a postdoctoral research associate in the Digital Signal Processing (DSP) group, Rice University, in 2016, where he received his M.S. and Ph.D. degrees from Rice University in 2014 and 2016, respectively.  He also attended the Georgia Institute of Technology as a visiting student in 2009.

Activities & Awards

Andrew serves regularly on program committees of several conferences on educational data mining, machine learning, and signal processing. He has also co-organized a series of workshops on machine learning for education; see http://ml4ed.cc/ for details. Some of his works have been integrated into OpenStax Tutor, a commercial-grade personalized learning platform.