Bayesian Network (BN)–based Learning Path Recommendation (LPR) systems are widely adopted in personalized education for modeling uncertainty and providing interpretable learner representations. However, existing studies predominantly evaluate these systems under controlled settings that assume balanced data, simplified curricula, and unconstrained resources. Consequently, limited empirical understanding exists regarding their performance in authentic classrooms. This study addresses this gap by examining the real-world deployment of a BN-based LPR system using naturally occurring classroom data. The system is evaluated using 426,004 quiz responses collected across 19 formative assessments,... More >