Online tools provide unique access to research students' study habits and problem-solving behavior. In MOOCs [Massive Open Online Courses], this online data can be used to inform instructors and to provide automatic guidance to students. However, these techniques may not apply in blended courses with face to face and online components. We report on a study of integrated user-system interaction logs from 3 computer science courses using four online systems: LMS [Learning Management System], forum, version control, and homework system. Our results show that students rarely work across platforms in a single session, and that final class performance can be predicted from students' system use. [For the full proceedings, see ED593090.]