Lehre

Ringvorlesung, in Kollaboration mit Professoren Flath, Winkelmann und Thiesse

Level: Bachelor

Scope: 4 SWS / 5 ECTS

In this course, students are introduced to the fundamentals of data science. The course covers the essential steps in the data science process, from data collection to analysis, modeling, and visualization. Students will learn key techniques and tools, including Python and popular libraries such as Pandas, Matplotlib and SciPy. Through practical examples and exercises, students will gain a solid understanding of the core principles of data science and how to apply them to solve real-world problems.

Learning Objectives

• Understanding the data science workflow, including data collection, cleaning, analysis, and visualization
• Learning the fundamental concepts and techniques in data analysis using Python
• Exploring the use of key Python libraries for data science such as Pandas, Matplotlib and SciPy
• Gaining the ability to apply basic machine learning models
• Understanding the importance of ethical data handling and reproducibility
• Building a foundation for more advanced topics in machine learning and artificial intelligence

Agenda

1. Introduction to Data Science
2. Python for Data Science Recap
3. Working with Data (Pandas)
4. Data Visualization (Matplotlib)
5. Getting and Collecting Data
6. Introduction to Machine Learning
7. Machine Learning Models
8. Time Series Analysis
9. Text Data and Natural Language Processing
10. Overview over Advanced Topics

Organization

Learning Materials on WueCampus:

• Jupyter Notebooks
• Datasets and exercises
• Uploaded solution template

Exam: written exam at the end of the semester

Level: Master

Scope: 4 SWS / 5 ECTS

In the course, students work on advanced data science projects. In this process, the entire data science workflow is followed, starting from data collection, through data preprocessing, to modeling, evaluation, and deployment. By using the top-down approach, students are empowered from the beginning to independently apply complex machine learning models.

Learning Objectives

• Getting to know the principles and frameworks in the research field of Data Science,
  presentation of numerous application examples
• Design, implementation and evaluation of the most important algorithms within an end-to-end workflow in the field of Data Science (including import of the data, their analysis and their processing)
• Application of Jupyter notebooks and their infrastructure (collection, storage, retrieval and analysis of data)
• Understanding of a data-based & analytical approach to decision-making problems
  Providing knowledge for the implementation and execution of solutions in the field of business analytics

Agenda

1. Introduction
2. Descriptive Analytics
3. Recap: Machine Learning
4. Feature Engineering
5. Deep Learning for Tabular Data
6. Deep Learning for Computer Vision
7. Deep Learning for Image Segmentation and Spatial Data
8. From Data to Production
9. Deep Learning for Natural Language Processing
10. Natural Language Processing with Huggingface
11. Guest Lecture

Organization

Learning Materials on WueCampus:

• Jupyter Notebooks
• Datasets and exercises
• Uploaded solution template

Exam: Final group project

Level: Bachelor

Scope: 4 SWS / 5 ECTS

The lecture is not offered every winter term. Please consult WueStudy to check out the offering for a specific semester!

In this course, students will become proficient in geospatial data science. Students learn essential tools for data manipulation, spatial data handling, and more advanced spatial data analytics techniques like clustering and spatial modeling. Students will gain the skills to extract meaningful insights from real-world geographical data and use them to solve business problems. The course covers both theoretical concepts as well as the necessary application-oriented tools (using Python and Jupyter notebooks) to become a skilled geospatial analyst ready to make data-driven decisions.

Content

• Spatial & non-spatial data manipulation in Python
• Displaying spatial information and creating maps in Python
• Exploratory Spatial Data Analysis
• Spatial Feature Engineering
• Models for Spatial Data Science

Organization

Links to infrastructure and all learning materials will be provided on WueCampus:

• Jupyter Notebooks
• Github classrooms & codespaces
• Datasets and exercises
• Solution templates

Examination: 

Students will need to solve small assignments throughout the semester. As final examination, students will work on a real-world geospatial data science problem and need to provide a written report including data & code-based evidence. 

Level: Bachelor

Scope: Lecture (2 SWS) and exercise session (2 SWS) / 5 ECTS

Learning Objectives

In this course, you will learn the concepts and terminology of simulation, as well as how to create and analyze simulation models using a simulation software package. You will also learn how to design and conduct simulation experiments, and how to validate and verify simulation models.

You will gain a solid foundation in probability and statistical analysis, which is essential for understanding and analyzing simulation results. You will also have the opportunity to explore a range of simulation applications in various fields, such as engineering, operations research, finance, and healthcare.

In addition, you will have the chance to apply these techniques to real-world problems through case studies.

Agenda

• Introduction to simulation: concepts, terminology, and applications.
• Probability and statistical analysis: probability distributions, random variables, statistical tests, and confidence intervals.
• Design of experiments: principles of experimental design, design of simulation experiments, analyzing simulation results.
• Validation and verification: techniques for validating and verifying simulation models, sensitivity analysis, and model robustness.
• Applications of simulation: examples of simulation applications in various fields, such as engineering, operations research, finance, and healthcare.
• Case studies: application of simulation techniques to real-world problems.
• Simulation software: overview of simulation software packages and their features, hands-on experience with a simulation software package.

Organization

Learning Materials on WueCampus and/or github:

• Lecture Slides
• Datasets and exercises

Level: Bachelor

Scope: Lecture (2 SWS) and exercise session (2 SWS) / 5 ECTS

Lecture in collaboration with Prof. Pibernik, Prof. Flath & Prof. Thiesse

As part of the digital transformation, the number of data sources about business and societal processes is continuously increasing. Decision-makers face the question of how these data can be used to develop more attractive products, improve processes, and increase customer satisfaction. The course "Data Driven Decisions (D3) in Practice" addresses how crucial business decisions can be made better with the help of "big" data. The focus of the course is the implementation of a structured process that includes the steps of problem definition and structuring, data collection and preprocessing, modeling and analysis, and decision-making.

This course is application-oriented and practical. Using several case studies from different industries and business areas (e.g., logistics, revenue management, marketing, etc.), real business problems are examined, demonstrating how companies can make better decisions with the help of extensive data. Participants learn to apply fundamental methods from the fields of optimization and data science and to build data analysis pipelines. A basic understanding or a strong willingness to learn the fundamentals of programming, data science, and optimization is expected.

Organization

Learning Materials on WueCampus and/or github:

• Lecture slides
• Datasets and case studies

Level: Master

Scope: Lecture (2 SWS) and exercise session (2 SWS) / 5 ECTS

Learning Objectives

In this course, you will learn

• the fundamentals for developing, deploying and maintaining machine learning systems in companies (MLOps),
• to design the associated IT infrastructure,
• to manage machine learning projects in organizations, including staffing and the choosing an appropiate organizational form.

You will refine and test your skills by practicing the theoretical concepts during exercise sessions. This practice will prepare you for the final project, where you and your peers will develop your own Machine Learning System.

Agenda

• Introduction to Enterprise AI
• Business Requirements for AI Systems
• ML Ops I: Data Engineering
• ML Ops II: Obtaining Training Data
• ML Ops III: Data Preprocessing
• ML Ops IV: Feature Engineering
• ML Ops V: Modeling & Evaluation
• ML Ops VI: Deployment
• ML Ops VII: System Monitoring 
• ML Ops VIII: Updating in Production
• Guest Lecture
• Instrastructure and Tools
• Managing Machine Learning Teams

Organization

Learning Materials on WueCampus and/or github:

• Lecture Slides
• Datasets and exercises
• Uploaded solution template

Exam: Final group project