Jin, X., & Kamarthi, S. (2025, June), Personalized Learning Paths: LLM-Based Course Recommendations in Manufacturing Education  Paper presented at 2025 ASEE Annual Conference & Exposition , Montreal, Quebec, Canada . https://peer.asee.org/57039

\bibitem{asee_peer_57039}
  Jin, X., \& Kamarthi, S. (2025, June), \emph{Personalized Learning Paths: LLM-Based Course Recommendations in Manufacturing Education}
  Paper presented at 2025 ASEE Annual Conference \& Exposition , Montreal, Quebec, Canada .
  https://peer.asee.org/57039

Xiaoning Jin and Sagar Kamarthi.  "Personalized Learning Paths: LLM-Based Course Recommendations in Manufacturing Education".  2025 ASEE Annual Conference & Exposition , Montreal, Quebec, Canada , 2025, June.  ASEE Conferences, 2025.  https://peer.asee.org/57039 Internet.  20 Aug, 2025

\bibitem{asee_peer_57039}
  Xiaoning Jin and Sagar Kamarthi.
  "Personalized Learning Paths: LLM-Based Course Recommendations in Manufacturing Education".
  \emph{2025 ASEE Annual Conference \& Exposition , Montreal, Quebec, Canada , 2025, June}.
  ASEE Conferences, 2025.
  https://peer.asee.org/57039 Internet.  20 Aug, 2025

@INPROCEEDINGS{asee_peer_57039
author = "Xiaoning Jin and Sagar Kamarthi"
title = "Personalized Learning Paths: LLM-Based Course Recommendations in Manufacturing Education"
booktitle = "2025 ASEE Annual Conference \& Exposition "
year = "2025"
month = "June"
address = "Montreal, Quebec, Canada "
publisher = "ASEE Conferences"
note = {https://peer.asee.org/57039}
}

TY  - CPAPER
AB  - This study presents a novel approach to developing a personalized course recommendation system tailored for online learners pursuing a specific curriculum. The system leverages a state-of-the-art Large Language Model (LLM) operating on structured curriculum data such as course introductions, module descriptions, syllabi, and learner-specific queries. By integrating this data, the system can generate precise course and module recommendations based on the learner's individual learning objectives, prior knowledge, and other relevant factors. Additionally, the system offers a transparent rationale for each recommendation, providing more intelligent and context-aware suggestions than traditional collaborative filtering or content-based recommendation systems. The system leverages the capabilities of LLMs, specifically GPT-4, using the Retrieval Augmented Generation (RAG) method for a content-based recommendation approach. The system generates accurate and context-aware responses by utilizing OpenAI's "text-embedding-3-large" model and Pinecone vector storage. Additionally, the study explores the integration of OpenAI Assistant APIs and Streamlit to build a user-friendly interface. This paper highlights the advantages of LLMs in addressing challenges in personalized recommendations, details the tests conducted, and discusses the results obtained. This advanced approach enhances the adaptability and relevance of users' learning experiences. We have also demonstrated this approach in our recently developed open curriculum on Data Science for Manufacturing, which showcases the system’s adaptability in real-world educational contexts.
AU  - Xiaoning Jin
AU  - Sagar Kamarthi
CY  - Montreal, Quebec, Canada 
DA  - 2025/06/22
PB  - ASEE Conferences
TI  - Personalized Learning Paths: LLM-Based Course Recommendations in Manufacturing Education
UR  - https://peer.asee.org/57039
ER  -