The course focuses on the practical application of data analysis and data management methods to an industrial use case. In interdisciplinary project groups, students independently structure and conduct a data analysis project based on the CRISP-DM process model. They define appropriate work packages and select, parameterize, and apply suitable methods for data acquisition, preprocessing, and modeling. The course builds on the methodological foundations of Industrial Data Science 1 and transfers them to a practical project setting. Particular emphasis is placed on the independent solution of an industrial problem, the structured implementation of the analysis process, and interdisciplinary collaboration.  

• CRISP-DM
• Industrial Data Analysis
• Data Acquisition
• Data Preprocessing
• Data Modeling
• Selection and Parameterization of Data Analysis Methods
• Interdisciplinary Project Work
• Industrial Use Cases

The effective use of data science in industrial practice requires more than knowledge of individual analysis methods. Industrial problems must be translated into structured data analysis projects, suitable methods must be selected and adapted to the available data, and solutions often need to be developed across disciplinary boundaries. Industrial Data Science 2 addresses these requirements through the independent processing of an industrial use case in interdisciplinary project groups. Students gain practical experience in structuring data analysis projects and applying methods for data acquisition, preprocessing, and modeling. The course therefore strengthens the methodological, project-related, and interdisciplinary competencies required for data-driven problem solving in industrial and engineering environments.  

• Schedule: Summer semester
• Format: Lecture (2 contact hours/week) and exercise (2 contact hours/week), 4 contact hours/week in total, 150 hours of workload, 5 CP
• Assessment: Presentation of results (approx. 10 min, 20%) and short report (80%) in english