This talk will present a study on students' engagement in e-learning environments where students work independently and solve problems without external supervision. We propose a new method to infer engagement patterns of users in such self-directed environments. We view engagement as a continuous process in time, measured along carefully chosen axes derived from student data in the system. We choose our axes from a non-supervised learning approach (Principal Component Analysis). We construct a trajectory of user activity by projecting the user's statistics along the selected PCs at regular time intervals. This approach is applied to a popular e-learning software for K12 math education that thousands of students use worldwide. We identify cohorts of users according to the way their trajectory changes over time (e.g., monotone up, down, constant, etc). Each cohort exhibits distinct behavioral dynamics and differs substantially in users' time in the e-learning system. Specifically, one cohort included students who dropped out of the system after choosing difficult problems they could not complete. In contrast, another cohort included students who chose more diverse problems and stayed longer in the system. In future work, these results can be used by teachers or intelligent tutors to track students' engagement in the system and decide whether and how to intervene. Bio: Dan Vilenchik holds a PhD in computer science from Tel Aviv University. He did a postdoc at UC Berkeley and UCLA. He is currently a tenured member of the Electrical and Computer Engineering School at Ben-Gurion University. His research includes various aspects of machine learning, such as the challenges of high-dimensional data, explainable AI, NLP, and multidisciplinary projects.