Temporal Dropout Risk in Learning Analytics: A Harmonized Survival Benchmark Across Dynamic and Early-Window Representations
arXiv:2604.08870v2 Announce Type: replace Abstract: Student dropout is a persistent concern in Learning Analytics, yet comparative studies frequently evaluate predictive models under heterogeneous protocols, prioritizing discrimination over temporal interpretability and calibration. This study introduces a survival-oriented benchmark for temporal dropout risk modelling using the Open University Learning Analytics Dataset (OULAD). Two harmonized arms are compared: a dynamic weekly arm, with models in person-period representation, and a comparable continuous-time arm, with an expanded roster of
The increasing adoption of large-scale online learning platforms and the critical need for student retention are driving advancements in learning analytics and predictive modeling.
This research provides a harmonized benchmark for evaluating temporal dropout risk in learning analytics, offering tools to improve student success and educational outcomes.
Educational institutions gain more reliable methods to predict student dropout, enabling proactive interventions and personalized support before it is too late.
- · Educational Institutions
- · Students
- · Learning Analytics Researchers
- · Ed-Tech Companies
- · Inefficient Educational Models
- · Unprepared Students
More effective student retention strategies are deployed across online learning platforms.
Improved educational completion rates lead to better-skilled workforces and higher societal productivity.
The application of sophisticated AI models becomes standard practice in educational management, profoundly altering teaching and learning paradigms.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG