We found that dropout prediction fortunately works almost equally on groups induced by various grouping factors. However, in the case of STEM majors, the predictor collection can vary as a …

Mar 18, 2024 · Drawing on twelve years of administrative data at a large public university in the US, we find that dropout prediction at the end of the second year has a 20% higher AUC than at the time of …

LAK 2017 Program Chairs’ Welcome We are very happy to welcome you to Vancouver, Canada, for the 7th International Conference on Learning Analytics and Knowledge (LAK’17). The Conference is …

We proposed a student's dropout prediction model using an intuitionistic fuzzy set and an XGBoost algorithm called STOU2PM. The system that collected student datasets from 2012 to 2022 consisted …

Mar 13, 2023 · Our data included complete LMS records of all courses taught at UC Berkeley between Spring 2017 and Spring 2021. The unit of analysis is time-stamped student or instructor interactions …

Prior studies on MOOC dropout prediction have encountered several challenges and limitations. First, these studies often relied on complex feature extraction processes, making it dificult to gen-eralize …

In this paper, we investigate the issue of using protected at- tributes in college dropout prediction in real-world contexts. Protected attributes are traits or characteristics based on which discrimination is …

Furthermore, we analyze real-world data from a course dropout prediction model to answer RQ2. Specifically, we use Newcombe’s Hybrid score method and bootstrapping to con-struct confidence …

We consider all students in higher education in Denmark who applied to higher education through the Danish centralized system between 2006 and 2017 and have finished their enrollment, resulting …

We demonstrate how existing MOOC dropout prediction pipelines can be made interpretable, all while having predictive performance close to existing tech-niques. We explore each stage of the pipeline …