The data created by web users while navigating on a website constitutes graph data. Large-scale graph data is generated on websites many users visit with high frequency. Analyzing large-scale graph data using artificial intelligence techniques and predicting user behavior by creating models is an actively studied research topic. Within the scope of this research, a machine learning business process is proposed that will allow the interpretation of graph data obtained from web user navigation data. A prototype application was developed to demonstrate the usability of the proposed business process. The developed prototype application was run on graph data obtained from websites with intense user-system interaction. A comprehensive evaluation study was carried out on the prototype application. The results obtained from the empirical evaluation are promising and show that the proposed business process is used.