Our project is motivated by the early dropout and low completion rate problem in MOOCs. We have extended traditional features for MOOC analysis with richer and higher granularity information to make more accurate predictions of dropout and performance. The results show that finer-grained temporal information increases the predictive power in the…

Early warning systems combine multiple data points, translate them into predictive indicators that are based on research, and proactively communicate them to stakeholders, so they can examine which students are or are not on track for postsecondary success and intervene accordingly. Early warning reports provide the student-level information…

Improving high school graduation rates has in recent years become a growing concern to state and local policymakers for a number of reasons: the reduced economic opportunities and increased social costs for individuals without a high school diploma; the economic consequences, such as reduced tax revenues; and the need for more college graduates.…