Embodied learning and the design of embodied learning platforms have gained popularity in recent years due to the increasing availability of sensing technologies. In our study, we made use of the Mathematical Imagery Trainer for Proportion (MIT-P) that uses a touchscreen tablet to help students explore the concept of mathematical proportion. The use of sensing technologies provides an unprecedented amount of high-frequency data on students’ behaviors. We investigated a statistical model called mixture Regime-Switching Hidden Logistic Transition Process (mixRHLP) that finds characteristic regimes and assigns students to clusters of regime transitions. To further the line of research and development, we explored whether we can predict students’ learning outcome or cluster of learning trajectories, as early as possible with both hand and eye movement data. The study informs teaching as tutors can utilize the predictions early and tailor instructions to the specific needs of students, based on real-time monitoring.