Personalized Learning Path Recommendation for System Integration and Architecture Through a Decision Tree–Based AI Engine

Lord Aeremist Pido Valdemoro; Edcel Bernabe Besa; Marc Daniel Rodriguez Lim; Anna Liza Ognita Villanueva; Jeusuel Nonnatus Noblezala De Luna

doi:10.36948/ijfmr.2026.v08i02.72258

Personalized Learning Path Recommendation for System Integration and Architecture Through a Decision Tree–Based AI Engine

Author(s)	Lord Aeremist Pido Valdemoro, Edcel Bernabe Besa, Marc Daniel Rodriguez Lim, Ms. Anna Liza Ognita Villanueva, Dr. Jeusuel Nonnatus Noblezala De Luna
Country	Philippines
Abstract	Traditional Learning Management Systems (LMS) often utilize a "one-size-fits-all" curriculum, failing to accommodate the diverse proficiency levels of students in complex technical courses like System Integration and Architecture (SIA). This lack of adaptability leads to a mismatch between learner needs and instructional content, reducing engagement and learning efficiency. This study aimed to design, develop, and evaluate LearnScope, an AI-powered adaptive e-learning system. The primary goal was to utilize a Decision Tree algorithm to classify student proficiency and automate the delivery of personalized learning paths. The study employed a Descriptive-Developmental research design following the Agile methodology. The system architecture utilized a hybrid stack with Moodle as the frontend and a Python/Flask microservice for the AI logic. The dataset consisted of historical academic records from 23 students, augmented with 11 synthetic records (N=34) to ensure class balance. A Decision Tree classifier was trained to categorize students into Beginner, Intermediate, and Advanced tiers. System quality was evaluated using ISO/IEC 25010 standards. The student cohort exhibited diverse learning capacities, with 12% identifying as "at-risk" (Beginner). The Decision Tree model achieved a prediction accuracy of 90.91%, with 100% recall for the critical "Beginner" class, ensuring no at-risk students were overlooked. User acceptance testing yielded a high usability rating (Weighted Mean = 3.85), though security measures received a moderate rating (2.69). LearnScope successfully demonstrates that interpretable AI models can effectively automate personalized instruction in resource-constrained educational settings. The system proactively identifies struggling learners and provides targeted interventions, though future iterations require enhanced security protocols for production deployment.
Keywords	Artificial Intelligence, Machine Learning, Personalized Leaning, Decision Tree, System Integration and Architecture, Learning Management System
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-04-03
DOI	https://doi.org/10.36948/ijfmr.2026.v08i02.72258

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

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

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Personalized Learning Path Recommendation for System Integration and Architecture Through a Decision Tree–Based AI Engine

Share this