DESIGN AND EVALUATION OF REAL-TIME ADAPTIVE LEARNING ALGORITHMS FOR PERSONALIZED K-12 CURRICULUM OPTIMIZATION USING STUDENT PERFORMANCE ANALYTICS

Maduabuchukwu Augustine Onwuzurike*, Joy Onma Enyejo, Amina Catherine Peter-Anyebe

ABSTRACT

The growing heterogeneity of learner abilities and pacing in K–12 education hasexposed fundamental limitations in static and batch-oriented curriculum deliverymodels. This study presents the design, implementation, and evaluation of a Real-TimeAdaptive Learning (RT-AL) framework for personalized K–12 curriculumoptimization using continuous student performance analytics. The proposed systemintegrates event-driven data ingestion, online learner state estimation, sequencebasedpredictive modeling, and constrained curriculum policy optimization to enableinstructional decisions within live learning sessions. Learner mastery was modeled asa continuously updated probabilistic state derived from correctness, response latency,and contextual interaction signals, allowing dynamic adjustment of contentsequencing, difficulty, and pacing. Empirical evaluation was conducted against fourbaseline approaches static curriculum sequencing, batch adaptive learning, rulebasedpersonalization, and random assignment using predictive accuracy, area underthe ROC curve (AUC), normalized learning gain (NLG), time-to-mastery reduction,engagement retention, and system latency as core metrics. Results show that RT-ALachieved superior predictive performance (accuracy = 0.91, AUC = 0.94),substantially higher learning gains (NLG = 0.42), and significantly lower responselatency (120 ms) compared to all baselines. Personalization effectiveness analysisacross diverse learner profiles revealed particularly strong gains for low priorknowledge and at-risk learners, while maintaining high calibration and enrichmentalignment for high achievers. Curriculum-level analysis demonstrated that real-timeadaptation enabled greater flexibility, deeper personalization, improved assessmentalignment, and sustained learner engagement relative to static designs. The findingsestablish that real-time, analytics-driven adaptation is not merely an optimizationenhancement but a structural requirement for effective personalized learning at scale.This study contributes a validated technical architecture, learner modeling approach,and evaluation framework that collectively advance the deployment of real-timeadaptive intelligence in K–12 education.

Keywords:

Adaptive Learning Algorithms; Personalized Curriculum; Student
Performance Analytics; Real-Time Learning Systems; K-12 Education Optimization.

Full Text Article