SmartPath: Personalized Learning Roadmap Generation and Course Recommendation using Transformers with LLM-Based Assessment

Sri Krishna Nikhilesh Chunduri; Appala Raju D; Ganesh Varma Chekuri; Haritha Kata; Jahnavi Kurmana

SmartPath: Personalized Learning Roadmap Generation and Course Recommendation using Transformers with LLM-Based Assessment

Author(s)	Mr. Sri Krishna Nikhilesh Chunduri, Mr. Appala Raju D, Mr. Ganesh Varma Chekuri, Ms. Haritha Kata, Ms. Jahnavi Kurmana
Country	India
Abstract	The rapid growth of digital learning resources has created a significant challenge for students in identifying structured learning paths that align with their skills, interests, and career goals. Conventional learning platforms often provide scattered educational materials without offering a personalized roadmap for skill development. This paper presents SMARTPATH, an AI-powered personalized learning roadmap generation system that assists engineering students in planning and managing their learning journey. The proposed system integrates transformer-based semantic embeddings and large language models within a scalable web-based architecture to generate customized learning roadmaps, recommend relevant courses, provide study materials, and automatically generate assessments for learner evaluation. The architecture consists of a React-based client interface, a FastAPI backend service, and an AI recommendation engine utilizing the MiniLM-L6-v3 pretrained embedding model from Hugging Face for semantic similarity computation. Personalized course recommendations are generated using cosine similarity between user skill embeddings and course dataset embeddings, eliminating the need for model training. Additionally, large language models are employed to dynamically generate topic explanations, learning materials, and evaluation assessments to support continuous learning. Experimental evaluation demonstrates a recommendation relevance score of 91.2% with an average system response latency of 295 ms, indicating that the proposed system provides an efficient and scalable solution for personalized learning guidance in engineering education.
Keywords	Personalized Learning, Learning Roadmap Generation, Course Recommendation, Transformer Embeddings, MiniLM-L6-v3, Large Language Models, Educational AI, Assessment Generation, Semantic Similarity
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-04-03

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

SmartPath: Personalized Learning Roadmap Generation and Course Recommendation using Transformers with LLM-Based Assessment

Share this