Researchers have developed a new protocol called LEAP (Leakage-Excluded Early-Availability Protocol) to address temporal leakage in early-warning models for Learning Management Systems (LMS). This protocol ensures that predictions are based only on information available at the time of prediction, preventing inflated performance metrics. When applied to the Open University Learning Analytics Dataset (OULAD), LEAP demonstrated that performance improves with a longer observation window, with Random Forest showing the best results at the earliest stages and Gradient Boosting outperforming later. The study also highlighted how temporal violations, particularly involving assessment data, can significantly skew early performance estimates. AI
IMPACT This research offers a method to improve the reliability of AI models used for predicting student outcomes, potentially leading to more effective interventions in educational settings.
RANK_REASON The cluster contains a research paper detailing a new protocol and its evaluation on a dataset.
- Gradient Boosting
- LEAP
- Learning Management System
- Open University Learning Analytics Dataset
- Random Forest
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →
