Upon completion of the course, students will be able to transfer industrial data sets and questions into data analysis problems. They will be able to confidently apply advanced statistical methods to industrial data sets. In addition, after completing the module, they will be able to select and apply appropriate machine learning methods for industrial problems. Furthermore, students will be able to assess the maturity level of data creation and collection in a digital factory and generate industrial data sets independently.

• Introduction to Industrial Data Science and the CRISP-DM
• Industrial Data Types and Time Series Analysis
• Data Management
• Exploratory Data Analysis and Visual Representation Techniques
• Association Rules, Correlation Analysis, and Pattern Discovery
• Data Preprocessing Methods and Feature Selection
• Model Selection Concepts and Performance Evaluation
• Classification via Decision Trees, Random Forests, and Support Vector Machines
• Advanced Machine Learning via Neural Networks, Deep Learning, and Clustering

The increasing use of modern information and communication technologies in manufacturing companies leads to continuously collected data. The evaluation and use of collected data, however, is crucial to the competitiveness of these companies. “Industrial Data Science 1” covers the basics of data mining and data management as well as their application in industrial practice in order to gain knowledge from data. The specific challenges faced by manufacturing companies are taken into account, and participants are taught the knowledge required to solve domain problems using data  analysis methods. There is a particular focus on data management, data preprocessing, model creation, and model evaluation. The module is offered to students belonging to the Department of Mechanical Engineering and the Departments of Statistics and Computer Science to enable joint learning and interdisciplinary knowledge exchange.  

• Schedule: Winter 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: written exam of 60 minutes in english