Deep learning-based recommendation system to address challenges in providing electronic services

AL Hinai, Turki Abdullah Masood and Al Kulaibi, Juma and Al Husaini, Mohammed Abdulla Salim and Al Husaini, Yousuf Nasser and Habaebi, Mohamed Hadi (2026) Deep learning-based recommendation system to address challenges in providing electronic services. In: 2025 10th International Conference on Computer and Communication Engineering (ICCCE), 26-27 August 2025, KOE, IIUM.

PDF - Published Version Restricted to Repository staff only Download (543kB) | Request a copy

Abstract

Abstract—In the era of digital transformation, universities are increasingly challenged to deliver personalized electronic services to students, particularly in areas like academic advising, GPA forecasting, and early warning systems. This study proposes an advanced academic performance prediction system using a Support Vector Machine (SVM) model, trained on a comprehensive dataset from 1,734 university students enrolled in the Spring 2024 semester. The dataset includes real and simulated GPA scores, academic classifications, warning records, and course registration details, providing a rich foundation for predictive analytics. The SVM algorithm, known for its robust classification capabilities in high-dimensional spaces, was implemented using MATLAB R2023b and evaluated on a system with an Intel Core i7 (14th Gen), 32 GB RAM, and an NVIDIA RTX 4070 GPU. The model classified students into three performance categories. It achieved a remarkable overall accuracy of 99.25%, correctly predicting 1,721 out of 1,734 instances. The precision for Class 1 and Class 2 was 100%, while Class 3 had a precision of 96.25%, with only 13 misclassifications. Furthermore, 10-fold cross-validation was employed to assess model generalizability, yielding accuracy scores ranging from 0.88 to 0.92, with Fold 4 scoring 0.89623. These results confirm the model’s robustness and suitability for real-world deployment in educational institutions.

Item Type:	Proceeding Paper (Plenary Papers)
Uncontrolled Keywords:	Deep learning, Recommendation System, Electronic Services.
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101 Telecommunication. Including telegraphy, radio, radar, television
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering > Department of Electrical and Computer Engineering Kulliyyah of Engineering
Depositing User:	Dr. Mohamed Hadi Habaebi
Date Deposited:	27 Apr 2026 11:39
Last Modified:	27 Apr 2026 11:39
Queue Number:	2026-04-Q2947
URI:	http://irep.iium.edu.my/id/eprint/128484

Actions (login required)

View Item