Advanced Analytics in Supply Chain Management



+49 241 80-93623



Teaching in winter term

The course Advanced Analytics in Supply Chain Management (Lecture + Exercise) is composed of lectures and exercises. Lectures and exercises follow the Inverted Classroom paradigm.
Recordings of lectures and exercises are made available and are accompanied by in-person lecture and exercise classes. Please note: Recordings and other material will remain available until the end of the semester.
Live sessions (lectures and exercises) are not recorded. During the live sessions, specific questions regarding the subjects treated in the recordings will be answered, there will be time for discussions, and the solutions to quizzes will be commented. Detailed information about lecture and exercise live sessions will be made available via Moodle.


The goal of this course is to enable students to formulate models and use methodologies to solve optimization problems in production planning and supply chain management.

The first and major part of the course focuses on prescriptive analytics. The fundamental concepts of production planning and scheduling systems will be discussed, linear and mixed integer programming models and exact and heuristic solution methods will be presented. Moreover, the basic concepts of stochastic programming will be introduced to enable students to tackle the uncertainty which characterizes supply chain problems (for example, uncertain demand or production capacity).

The second part of the course will focus on predictive analytics. An overview of data preprocessing techniques and main forecasting methods will be provided, and machine learning techniques for scheduling problems will be presented. Through exercise classes and case studies, students will enhance their problem-solving skills, and they will learn how to solve real-world production planning problems using Python and Gurobi.


Language: English
Prerequisites: Operations Research 1 or similar knowledge helpful
Grading: 100% exam + bonus possible: Quizzes will be asked during classes. By completing at least 75% of them successfully, the final grade will be increased by one grade step, e.g., from 2.0 to 1.7. Three exercise tasks will be assigned during the course. By completing at least two of them successfully, the final grade will be increased by an additional grade step.

Learning Goals

  1. master the fundamental concepts of production planning and scheduling systems
  2. formulate mathematical models (both deterministic and stochastic mixed integer programming models) to represent production planning problems
  3. master state-of-the-art optimization techniques and reformulation results to solve supply chain problems
  4. master the use of Python and Gurobi to solve production planning problems in practice.

External Links