Published September 11, 2025 | Version v1
Journal Open

Development of NeuraCraft: An AI-Powered Adaptive E-Learning Platform for Personalized Education

  • 1. Centro Escolar University, Manila, Philippines

Description

NeuraCraft is an AI-powered adaptive eLearning platform that personalizes learning paths based on individual student needs and performance, addressing significant gaps in existing educational technology. The platform incorporates machine learning techniques, gamification elements, and social learning features, grounded in established learning theories such as Vygotsky's Zone of Proximal Development and Bloom's Mastery Learning. Developed using an agile methodology and cutting-edge technologies including Next.js, MySQL with Prisma ORM, and Python-based recommendation systems, NeuraCraft demonstrated strong performance across various metrics during quality assurance and user acceptance testing. The platform successfully implements Bayesian Knowledge Tracing algorithms to dynamically adjust content difficulty and provide personalized recommendations, creating a learning environment that adapts to each student's unique abilities and learning pace. Results indicated high user satisfaction, with substantial improvements reported in learning experiences compared to traditional methods. This research demonstrates NeuraCraft's significant alignment with United Nations Sustainable Development particularly contributing to targets 4 (Quality Education), 9 (Industry, Innovation, and Infrastructure), and 10 (Reduced Inequalities) goals, through its inclusive, equitable, and technology-enhanced educational approach. Future research directions include expanding compatibility, enhancing error handling, broadening content coverage, and conducting longitudinal studies to assess effectiveness across diverse learner types and educational contexts. This research makes a significant contribution to the field by demonstrating the effectiveness of AI-driven personalization in educational contexts and providing a comprehensive framework for future adaptive learning systems.

Files

GRSMRS202509006 Gallery Proof.pdf

Files (697.8 kB)

Name Size Download all
md5:a4d07cfb381a4b744739915ae257c2c1
697.8 kB Preview Download