Edinburgh Napier University

  The study introduces a machine learning model for BMM (Building Maintenance Management), which utilized IPA (Intelligent Process Automation) to predict the material stock required in a period, to manage the cost efficiency. Traditional BMM approaches often prepared not efficient amount of material stock for pending maintenances required materials, that could be resolved by this machine learning model, it use discipline-sensitive machine learning algorithms to predict material needs accurately, ensure the efficient amount of material stock levels and reducing the financial waste. A proof-of-concept implemented in a case study from this industry that validates the machine learning model’s effectiveness, showing the capability of combining Artificial Intelligence (AI) and machine learning to apply the material stock level prediction. The proposed approach not only predicts the material stock efficiency but also ensures the methodology of AI could be utilized in BMM, which could be further attached to smart urban development. With the support of the case study, the introduction of this approach could make the BMM field a significant advancement AI-powered material stock management. It resolved both manufacturer production waste and unnecessary finance cost, helping reduce resource waste and promoting sustainability. The outcomes of this research include improved accuracy in forecasting material stock levels for upcoming building maintenance tasks, explore in this area with more sophisticated AI algorithms, mathematic, and analytics, also considered the potential IoT integration in the material warehouse to analyze and predict in real time material stock level. In a broader context, we are introducing a new standard of material stock management that could collaborate with AI together to enhance the BMM in a smart urban environment.