Skip to content
Open access

AI-Based Predictive Framework for Student Behavior Analysis and Performance Forecasting in Smart Learning Environments

Sep 2026 · JOIV: International Journal on Informatics Visualization · Vol 10, pp. 2286 · 0 citations

TL;DR

This study designs and validate an AI-driven Effective Teaching-Learning Model (AID-ETLM) that improves personalized learning through advanced Deep Neural Networks (DNNs) and outperforms baseline frameworks including Smart Education Model, Artificial Neural Network, Big-Data with AI Education, and the Deep Learning Model.

Abstract

The advances in Artificial Intelligence (AI) and Machine Learning (ML) have transformed education, particularly in adaptive e-learning environments. Traditional teaching methodologies face challenges in monitoring student progress, adapting instruction, and optimizing the learning experience. The objective of this study is to design and validate an AI-driven Effective Teaching-Learning Model (AID-ETLM) that improves personalized learning through advanced Deep Neural Networks (DNNs). The materials and methods consist of a teacher-student DNN ensemble combined with a Knowledge-Distillation pipeline, evaluated on multi-modal interaction logs collected from a real e-learning platform, where engagement, learning preferences, and teacher-student interactions are extracted in real time. The model implements a dual-prediction mechanism that fuses forecast scores with example gradients to dynamically refine instructional strategies and drive adaptive content recommendation. The paper reports five performance dimensions: student performance ratio, efficiency ratio, evaluation-score analysis, student interaction ratio, and learning-style prediction. The results show that AID-ETLM improves student engagement by 27%, content-retention rate by 19%, and outperforms baseline frameworks including Smart Education Model (FSEM), Artificial Neural Network (ANN), Big-Data with AI Education (BD-AIE), and the Deep Learning Model (DLM). An ablation study, paired statistical-significance testing (p < 0.001), and computational-complexity analysis confirm that every component of the model contributes a measurable gain and that AID-ETLM remains practical for deployment on standard institutional servers. This suggests integrating pedagogical strategy with AI-driven adaptation to build a resilient, intelligent e-learning ecosystem that delivers consistent instructional quality, interactive student success, and a more engaging digital education paradigm.

Read PDF

Similar papers

Open access 2026

Hybrid Machine Learning-based Optimization for Student Academic Performance Forecasting: An E-learning Data Mining Approach

—The rapid expansion of e-learning systems has transformed modern education by generating large volumes of student interaction data, creating new opportunities for monitoring and predicting academic performance. However, accurately measuring student achievement in digital learning environments remains challenging due t...

S. Praveen, N. S. K. M. K. Tirumanadham, S. Adusumalli et al. · 0 citations
Open access Sep 2026

Enhancing student performance prediction using an optimized RNN-LSTM model: a step towards personalized education

Learning Analytics is an emerging field that strives to analyze and predict trends in student performances over time. With the increased usage of Learning Management Systems (LMS), which are equipped with learning content, interaction, and assessment aligned with educational objectives, advanced machine learning techni...

J. D. Joann, M. Balasubramanian, A. S. Nisha et al. · 0 citations
Open access Sep 2026

An artificial intelligence driven adaptive learning system for enhancing student engagement and academic achievement in STEM education

The results show that the proposed framework can support behavioral engagement-proxy classification, achievement forecasting, STEM knowledge tracing, adaptive recommendation, and explainable education decision support.

Lan-Lan Zhang, Zhen-Ping Zhang · 0 citations
Review Open access Oct 2026

AI Agent-Based Intelligent Learning System for Personalize Education, Student Performance Prediction and Adaptive Content Generation

Personalized education requires more than predicting whether a learner will pass a course. Predictions must support appropriate learning activities, while generated explanations must remain accurate and aligned with the curriculum. This paper proposes an AI agent-based intelligent learning system integrating learner pr...

Rani Suman · 0 citations
Conference Oct 2026

A prediction model for higher education learning behaviors based on deep learning

With the rapid advancement of deep learning technology, research on intelligent models centered on learning behavior prediction has become a key direction in higher education informatization. Addressing the challenges of complex and highly temporal student behavior patterns in university online learning environments, t...

Kai Wang, Yan Wang, Lei Xing · 0 citations
Conference Open access Sep 2026

Adaptive Learning in Online Education Using Artificial Intelligence: A Systematic Survey of Techniques, Challenges, and Future Directions

Online learning platforms have significantly transformed modern education by providing flexible, scalable, and accessible learning opportunities. However, conventional e-learning systems continue to follow a one-size-fits-all model, delivering uniform content regardless of individual learner needs, pace, or prior knowl...

Pavan Mahantesh Kurubar, C. H, H. P. Mohan Kumar · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.