Personalized course recommender for diverse skills and certifications

March 8th, 2023

This thesis topic would involve researching and developing a recommender system, integrated with Large Language Models (LLMs), that can take into account users’ diverse skills and certifications, and provide personalized course recommendations that align with their career goals and interests. The thesis could explore different machine learning algorithms and data processing techniques to optimize the system’s accuracy and efficiency. It could also involve user testing and evaluation to assess the effectiveness and user satisfaction with the recommender system.

Thesis Type
  • Master
Tao Wu
Proposal on
22/08/2023 9:30 pm
Proposal room
Seminar room I5 6202
Presentation room
Seminar room I5 6202
Stefan Decker
Matthias Jarke
Fateme Fathi
Sulayman K. Sowe

In our currently running project MyEduLife – The blockchain as a tool for decentralized storage of individual continuing education biographies, we focus on providing digital certificates of further education whose hashes are stored in a blockchain and on which the acquired skills and competencies are standardized and machine-readable.

With the abundance of online courses and learning resources available, it can be challenging for learners to identify the most suitable courses to meet their learning objectives. A personalized course selection and study planning recommender system can help learners select courses that align with their existing skills and certificates, and create study plans that optimize their learning experience.

This thesis aims to develop a recommender system, integrated with Large Language Models (LLMs) for personalized course selection based on a user’s existing skills and certificates. The system will analyze a user’s skill set and certification history to suggest relevant courses and learning materials to achieve their learning objectives. Leveraging the advanced natural language understanding capabilities of LLMs, the thesis will investigate various machine learning algorithms and data processing methodologies to refine the accuracy and efficiency of the recommender system. The proposed system will also include a user interface for course selection, allowing users to search and browse for courses and provide feedback on their experience. The effectiveness of the system will be evaluated through user testing and feedback, with the goal of providing a useful tool for learners to achieve their learning objectives efficiently and effectively.

  • Must:
    • Machine Learning and Data Science
    • Containerization & Orchestration Tools: Docker, Kubernetes
    • Web Development Tools
  •  Beneficial:
    • Natural Language Processing (NLP)
    • Database Management
    • Cloud Computing