GenAI Based Framework for Personalized Training Recommender in Energy Sector

As the energy industry rapidly evolves, the challenge of keeping employees up to date is growing. Traditional training plans and programs no longer meet the demands of modern roles which led to outdated, repetitive, and generic learning outcomes. This paper investigates the effectiveness of Generative AI based training recommender systems aiming to provide tailored, personalized course recommendations to yield higher employee engagement, and faster upskilling. Natural language processing, machine learning, and knowledge graph techniques are integrated to better comprehend employees’ current skills and needs. By using a two-pass filter, the system first analyzes the profile of the employee, then delivers customized training material suggestions, while Large Language Model (LLM) fine-tuning ensures that recommendations remain up-to-date and contextually accurate. The research findings are promising, as the employees who received training using the system demonstrated more engagement and better job performance than those using traditional methods. The effectiveness of the Generative AI-based training recommender system was evaluated through a survey of more than two hundred employees, comparing the perceived usefulness, relevance, and impact of the recommended courses on their job performance and engagement between the new system and traditional training methods. The results were analyzed using both qualitative and quantitative methods, including statistical comparisons of mean scores and standard deviations, to confirm the significant benefits of the new system.