<p>Currently, the selection of cutting tools and machining conditions primarily relies on the individual experience and knowledge of machining engineers, leading to substantial processing time for appropriate tool selection. In this study, as a preliminary step toward digitalizing the cutting tool selection process, we developed a fundamental study to predict the mechanical properties of cemented carbide tools based on their chemicalcomposition and manufacturing process conditions. To predict the key properties of WC-based tool materials hardness and fracture toughness we collected 1,024 data entries from 265 related studies and used them for training prediction models. Various machine learning and multilayer perceptron models were employed to analyze the effects of manufacturing process conditions on the physical property of WC-based tool materials. Among the predictive models, the XGBoost model was selected as the final model due to its superior predictive performance and advanced optimization capabilities. Through hyperparameter optimization, the selected prediction model achieved a prediction accuracy of 91.88% for hardness and 86.62% for fracture toughness. The findings of this study demonstrate that the mechanical properties required for WC-based tools can be predicted within a certain range based on manufacturing process conditions and chemical composition.</p>