This study investigates the use of educational data mining (EDM) techniques to predict student performance and enhance learning outcomes in higher education. Leveraging data from Moodle, a widely used learning management system (LMS), we analyzed 450 students’ academic records spanning nine semesters. Five machine learning algorithms—k-nearest neighbors, random forest, logistic regression, decision trees, and neural networks—were applied to identify correlations between courses and predict grades. The results indicated that courses with strong correlations (+0.3 and above) significantly enhanced predictive accuracy, particularly in binary classification tasks. kNN and neural networks emerged as the most robust models, achieving F1 scores exceeding 0.8. These findings underscore the potential of EDM to optimize instructional strategies and support personalized learning pathways. This study offers insights into the effective application of data-driven approaches to improve educational outcomes and foster student success.

Personalized learning environments increasingly rely on learner modeling techniques that integrate both explicit and implicit data sources. This study introduces a hybrid profiling methodology that combines psychometric data from an extended Felder–Silverman Learning Style Model (FSLSM) questionnaire with behavioral analytics derived from Moodle Learning Management System interaction logs. A structured mapping process was employed to associate over 200 unique log event types with FSLSM cognitive dimensions, enabling dynamic, behavior-driven learner profiles. Experiments were conducted across three datasets: a university dataset from the International Hellenic University, a public dataset from Kaggle, and a combined dataset totaling over 7 million log entries. Deep learning models including a Sequential Neural Network, BiLSTM, and a pretrained MLSTM-FCN were trained to predict student performance across regression and classification tasks. Results indicate moderate predictive validity: binary classification achieved practical, albeit imperfect accuracy, while three-class and regression tasks performed close to baseline levels. These findings highlight both the potential and the current constraints of log-based learner modeling. The contribution of this work lies in providing a reproducible integration framework and pipeline that can be applied across datasets, offering a realistic foundation for further exploration of scalable, data-driven personalization.

Personalized learning environments increasingly rely on learner modeling techniques that integrate both explicit and implicit data sources. This study introduces a hybrid profiling methodology that combines psychometric data from an extended Felder–Silverman Learning Style Model questionnaire with behavioral analytics derived from Moodle Learning Management System interaction logs. A structured mapping process is employed to associate over 200 unique log event types with FSLSM cognitive dimensions, enabling dynamic, behavior-driven learner profiles. To evaluate the effectiveness and generalizability of the approach, experiments were conducted across three large-scale datasets: a university dataset from the International Hellenic University, a public dataset from Kaggle, and a combined dataset totaling over 7 million log entries. Deep learning models—including a Sequential Neural Network, BiLSTM, and a pretrained MLSTM-FCN—were trained to predict student performance across regression and classification tasks. Results show high accuracy in binary classification, moderate success in 3-class prediction, and limited effectiveness in fine-grained grade regression and 11-class classification. The proposed framework demonstrates the potential of combining static and behavioral data for scalable personalization in smart learning systems, paving the way for more adaptive, data-driven educational interventions.

It is a fact that educational institutions at all levels are now focusing their attention on analyzing the behavior and performance of their students. The main objective of this study is to examine whether it is possible to predict the grades of students in the Department of Computer, Informatics and Telecommunications Engineering (ICT) at the International Hellenic University (IHU), in a course, based on their performance in previous related courses within real error margins, as well as the optimization of the prediction error. Different models were used for prediction in order to evaluate the performance and impact of each model separately. The goal of this work is to provide significant results regarding the long-term performance of the students. The models used were capable of predicting the performance within the defined absolut error margin.