The manufacturing of bioceramic dental crowns is an urgent matter for research-ers in the dental sector. Hence, optimizing the bioceramic manufacturing process is a critical step that impacts quality, efficiency, and cost. Selecting the appropri-ate manufacturing process depends on several criteria that make it a mul-ti-criteria-decision- making (MCDM) problem. The research aims to develop a machine learning model to optimize the manufacturing process which consists of two stages, the first stage is a decision tree supervised machine learning model in which the dataset collected from previous reviews and articles is composed of product specifications as inputs and suitable manufacturing process groups that are classified into formative casting, formative molding, traditional subtractive, nontraditional subtractive and additive as output is fed into the model, trained using regression analysis and validated using mean absolute deviation(MAD), then in the second stage, Processes of the best group are optimized using two methods, FUZZY-AHP which weighs the selection criteria with the target, and FUZZY-TOPSIS which ranks such criteria and gets most appropriate bioceramic dental crowns manufacturing process. The model can predict the best appropriate bioceramic dental crowns manufacturing process which is a Vat photopolymerization in case of feeding the model with bioceramic dental crowns features.