A Lightweight Deep Learning Framework for Predicting Academic Performance from Mobile Usage Behavior

Author(s)	Ms. Vimala S, Prof. Dr. G.Arockia Sahaya Sheela
Country	India
Abstract	This research presents a computationally efficient deep learning framework designed to forecast student academic outcomes by analyzing smartphone usage patterns. The architecture combines convolutional neural networks, bidirectional recurrent layers, and attention-based feature weighting while implementing model compression techniques to enable deployment on resource-constrained devices. Testing on behavioral logs from 287 undergraduate students demonstrated strong predictive capabilities and practical applicability for identifying students at academic risk. Key behavioral indicators—including the frequency of application switching, engagement with educational tools, and the variability of usage patterns—emerged as critical factors influencing academic success.
Keywords	Academic Performance Prediction, Mobile Usage Behavior, Deep Learning, Attention-Based Models, Student Risk Assessment
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 7, Issue 6, November-December 2025
Published On	2025-12-24
DOI	https://doi.org/10.36948/ijfmr.2025.v07i06.64050

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research