Synthesizing CRISP-DM and Quality Management: A Data Mining Approach for Production Processes

This paper presents the QM-CRISP-DM for data mining applications in the context of production process improvement. It proposes concrete quality management tools for every phase of the CRISP-DM cycle. Especially for beginners, the described phases of the CRISP-DM cycle are often too general. As process improvement and error analysis are core competencies of quality management, there exist many tools with the potential of also supporting data analytics and mining projects. Therefore, we synthesize quality management tools with the CRISP-DM methodology to provide a user guide for data mining beginners. The presented QM-CRISP-DM is validated in a data mining project for the development of an error forecasting system in the field of electronics production.