Ranjit Paul 1), Asmaa Mohamed 2), Peren Canatalay 3), Ashima Kukkar 4), Sadiq Hussain 1), Arun Baruah 1), Jiten Hazarika 1), Silvia Gaftandzhieva 5), Esraa Mahareek 2), Abeer Desuky 2), Rositsa Doneva 5)
1) Dibrugarh University, Dibrugarh (India)
2) Al-Azhar University (girls branch), Cairo (Egypt)
3) Istinye University, Istanbul (Turkey)
4) Chitkara University, Punjab (India)
5) University of Plovdiv “Paisii Hilendarski”, Plovdiv (Bulgaria)
https://doi.org/10.53656/math2025-6-4-obc
Abstract. The paper proposes a comprehensive student academic performance prediction approach by integrating machine learning with metaheuristic optimization. Initial models (Logistic Regression, Decision Tree, Random Forest, MLP) were refined using boosting techniques (Gradient Boosting, XGBoost, LightGBM), with XGBoost achieving 95.59% accuracy. Eight modern optimization algorithms were applied for feature selection to enhance model efficiency and interpretability, with the Grey Wolf Optimizer and the Heap-Based Optimizer outperforming others in key metrics. Support Vector Machine algorithms applied after feature selection strengthened the predictive capability of the selected feature subsets. The research outcomes demonstrate that uniting boosting approaches with feature selection algorithms enables the creation of reliable and scalable predictive models that detect student success and failure earlier.
Keywords: Machine Learning, Optimization Algorithms, Educational Data Mining, Ensemble Models, Boosting Algorithms.
Свързани статии:
Exploring the Nexus of Psychological Safety and Physical Health in the Workplace: A Machine Learning Augmented Study
Artificial Intelligence in Cybersecurity: Rigorous Critical Review, Methodological Challenges and Future Research Directions
Predicting Student Academic Performance: Modern Approaches and Techniques
Exploring the Impact of Self-Efficacy on Well-Being in University Students
