Citation

Nabi, Md Serajun and Islam, Sumiya and Ahmad Fauzi, Mohammad Faizal and Bannah, Hasanul and Mohiuddin, Golam Md and Abdullahi, Muhammad Kabir (2025) Adaptive Learning for Elementary Students Using AI to Support Individual Learning Styles. In: 2025 Multimedia University Engineering Conference, MECON 2025, 21 July 2025 - 23 July 2025, Cyberjaya, Malaysia.

Text IEEE Xplore Full-Text PDF_16.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

Adaptive learning is essential at the elementary level, but the traditional approach to teaching cannot meet individual learning patterns. This study examines AI-based adaptive learning by combining Machine Learning algorithms to predict learners’ learning patterns and academic achievements. Using a hybrid approach, XGBoost as a feature selection model, and a neural network for prediction, the study examines students’ data from Yogyakarta City to build a personalized recommendation system. The model achieved MSE: 4.60, MAE: 1.66, RMSE: 2.14, with good predictive accuracy. However, the R² score (0.56) shows moderate strength, and there are other influencing factors for student performance. The results highlight the potential of AI-driven adaptive education systems for data-driven decisionmaking in personalized learning strategies. Future research must prioritize real-time learning analytics, multimodal AI integration, and scalable AI-based classroom solutions to enhance the applicability of adaptive education.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Elementary education, adaptive learning
Subjects:	L Education > L Education (General)
Divisions:	Faculty of Information Science and Technology (FIST) Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	17 Mar 2026 05:13
Last Modified:	17 Mar 2026 05:13
URII:	http://shdl.mmu.edu.my/id/eprint/15481

Downloads

Edit (login required)