Industry 4.0 (I4.0) and digital transformation are revolutionizing maintenance in industries, pushing it towards a more intelligent and proactive approach, known as smart maintenance (SM). Recently, the transition to Maintenance 4.0 has been experienced, where maintenance decisions based on data and advanced analytics brought about by SM make it possible to increase efficiency, reduce operating costs and have a major impact on operational performance. With the increasing digitalization of processes and the availability of new technologies, decisions are becoming smarter, which requires having a structured, data-driven decision-making process for efficient decisions. However, making management decisions can be complex due to the multiple criteria and points of view involved. For example, there can be trade-offs and different competing priorities between functional areas such as maintenance, production and finance. From this perspective, it is crucial to have a methodology that combines these conflicting aspects, and in the Maintenance 4.0 era, the consideration of multiple criteria and points of view justifies the need for a decision support framework that combines multi-criteria decision making (MCDM) and Machine Learning (ML) techniques. A scoping review showed that there is a lack of decision support methodologies (and frameworks) combining these approaches in empirical studies and in emerging countries. In view of this, this research aims to propose and apply a decision support framework for MS in a Brazilian manufacturing company. A case study is used as the empirical method, using real maintenance data, participant observation and interviews, as well as document analysis. A hybrid multi-criteria approach is proposed using AHP, MOORA, MULTIMORA and Borda methods with qualitative and quantitative data, to solve a problem of ranking printers to be part of the start of predictive maintenance. The computational implementation of the approaches that make up the methodology took place in Python. At the end of the research, it was possible to observe that the combination of MCDM and ML can be an effective approach to improve decision-making in asset maintenance, considering multiple criteria and the complexity of the data involved.