Hybrid Learning for Smart Education Platforms and Personalized Learning Systems
Download PDFAbstract
The evolution of digital education has paved the way for highly adaptive and personalized learning experiences. This chapter delves into the domain of Hybrid Intelligent Systems (HIS) and their application in creating smart education platforms. We propose a novel hybrid learning framework designed to predict student performance and facilitate the generation of personalized learning paths. The core of this framework is a predictive engine that leverages a hybrid ensemble model, combining the strengths of Random Forest, Gradient Boosting, and a Multi-Layer Perceptron (MLP) neural network. A comprehensive simulation is conducted on a synthetic dataset, meticulously crafted to mirror the complex interactions within a real-world learning environment. The performance of the proposed hybrid model is rigorously evaluated against its constituent models using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R2). The results underscore the potential of HIS to significantly enhance the efficacy of educational platforms by providing accurate performance predictions, which are crucial for dynamic content recommendation and adaptation.
References
- Wesam Ahmed et al. “Machine learning-based academic performance prediction with explainability for enhanced decision-making in educational institutions”. In: Scientific Reports 15.1 (2025), p. 26879.
- Jing Wang and Yun Yu. “Machine learning approach to student performance prediction of online learning”. In: PloS one 20.1 (2025), e0299018.
- Aymane Ezzaim et al. “AI-based learning style detection in adaptive learning systems: a systematic literature review”. In: Journal of Computers in Education (2024), pp. 1–39.
- Alaa O Khadidos et al. “Personalized learning in hybrid education”. In: Scientific Reports 15.1 (2025), p. 18176.
- Emmanuel Nwelih and Victor Osasu Eguavoen. “Enhancing Smart Education: Comparative Analysis of Hybrid Recommendation Algorithms for Personalized Learning”. In: Quantum Journal of Engineering, Science and Technology 6.1 (2025), pp. 125–132.
- Alok Kumar Pani et al. “Hybrid Knowledge-Enhanced Personalized Learning Recommendation Model for Adaptive and Intelligent Educational Systems”. In: 2025 2nd International Conference on Software, Systems and Information Technology (SSITCON). IEEE. 2025, pp. 1–6.
- Deepak Kem. “Personalised and adaptive learning: Emerging learning platforms in the era of digital and smart learning”. In: International Journal of Social Science and Human Research 5.2 (2022), pp. 385–391.
- Kwang Sik Chung and Wen-Hao David Huang. “Hybrid learning cloud platform with private cloud platforms and public cloud platforms for smart learning”. In: The 2013 WEI international academic conference proceedings. 2013, pp. 30–33.
- Siyu Wu et al. “A comprehensive exploration of personalized learning in smart education: From student modeling to personalized recommendations”. In: arXiv preprint arXiv:2402.01666 (2024).
Principles of Hybrid Intelligent Systems
