Physics Education Research has helped support and enhance physics education through a wide variety of research studies. In fact, some of the most compelling evidence for making use of evidence-based teaching methods stem from quantitative research studies in PER. Until recently, this work has employed traditional statistical and modeling techniques such as the analysis of the variance and linear regression. As educational data have become more plentiful and complex, quantitative physics education researchers have begun to revisit how we develop and conduct research studies. Some have started to borrow approaches from other fields including data science. In this talk, we will explore the use of machine learning techniques in education research through a series of studies being actively conducted by the Learning Machines Lab, a research collaboration between Michigan State University and the University of Oslo. How the group supports undergraduate researchers to engage with this work will also be highlighted. The work presented has been supported by the National Science Foundation, MSU’s College of Natural Science, UiO’s Center for Computing in Science Education, and the Olav Thon Foundation.