A new pipeline called UBP-CAP has been developed to integrate student performance prediction and metacognitive calibration within intelligent tutoring systems. This framework processes student behavioral telemetry through three modules: a LightGBM classifier for correctness prediction, calibration metrics to evaluate metacognitive alignment, and a crossed Generalized Linear Mixed-Effects Model for decomposing calibration deviations. The research introduces the Predictive-Explanatory Divergence Index (PEDI) to quantify structural divergence between predictive and explanatory feature profiles, with findings indicating that student naive ECE significantly exceeds model ECE, suggesting systematic miscalibration. AI
IMPACT This research could lead to more personalized and effective intelligent tutoring systems by improving the accuracy of student performance prediction and understanding of metacognitive alignment.
RANK_REASON Research paper detailing a new pipeline and metrics for student performance prediction and metacognitive calibration. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
