This thesis explores how Machine Learning (ML) can enhance the assessment of reusability potential in the sustainable renovation of Amsterdam’s bridges and quay walls. As the city faces the urgent task of renovating large parts of its aging infrastructure, sustainable renovation strategies such as material reuse are gaining importance. However, assessing the reusability potential of existing structural components remains a complex challenge that is not only shaped by technical factors, but also by the influence of various stakeholders involved throughout the renovation process. The research combines a literature review, stakeholder interviews, and the development of a machine learning model trained on data from 20 completed and ongoing bridge and quay wall renovation projects in Amsterdam. It examines both the technical data and stakeholder related insights, by investigating how technical factors, stakeholder roles and priorities affect reuse decisions.