The proliferation of mobile devices has changed the way digital information is consumed and its efficacy measured. These personal devices know a lot about user behavior from embedded sensors along with monitoring the daily activities users perform through various applications on these devices. This data can be used to get a deep understanding of the context of the users and provide personalized services to them. However, there are a lot of challenges in capturing, modeling, storing, and processing such data from these systems of engagement, both in terms of achieving the right balance of redundancy in the captured and stored data, along with ensuring the usefulness of the data for analysis. There are additional challenges in balancing how much of the captured data should be processed through client or server applications. In this article, we present the modeling of user behavior in the context of personalized education which has generated a lot of recent interest. More specifically, we present an architecture and the issues of modeling student behavior data, captured from different activities the student performs during the process of learning. The user behavior data is modeled and sent to the cloud-enabled backend where detailed analytics are performed to understand different aspects of a student, such as engagement, difficulties, and preferences and to also analyze the quality of the data.