Adaptive Hybrid Model for Academic Performance Prediction and Learning Strategy Recommendation

Abstract

Academic performance prediction is important for helping lecturers identify student learning needs before academic problems become difficult to address. However, students differ in learning preferences, engagement, prior knowledge, and academic achievement, making uniform learning strategies less effective. This study proposes an adaptive hybrid model for academic performance prediction and learning strategy recommendation by integrating K-Means Clustering, Simple Additive Weighting, and an Artificial Neural Network. The dataset consists of 74 student samples containing VARK learning preferences, engagement scores, pretest scores, and GPA-like academic indicators. After data cleaning, median imputation, and standard scaling, K-Means was applied to segment students into five learning profiles. Cluster centroids were then transformed into three decision criteria, namely Engage, Retention, and Effort. Simple Additive Weighting was used to rank three learning strategies: Micro-video Learning, Quiz Drill Practice, and Peer Discussion. The resulting recommendation labels were used together with the academic features to train an Artificial Neural Network for performance prediction and strategy classification. The evaluation showed that both models achieved an unrounded accuracy of 99.63%, while the rounded classification report displayed nearly perfect precision, recall, and F1-score. These findings indicate that the proposed integration can support data-driven adaptive learning decisions. Nevertheless, the high performance should be interpreted carefully because the dataset is limited and comes from a single institutional context. Further validation with larger, more diverse datasets is required to confirm generalizability.

GS Cited Analysis