Combining Operations Research and Data Science
Kombination von Operations Research und Data Science
6 CPWinterEN
Prerequisites
Recommended, as written
• Basics of Python programming, • basics of linear programming, • basics of probability distributions
Contents
• Introductory Case Study, Representing and Computing with Uncertain Quantities • Obtaining Probability Distributions and Probabilistic Machine Learning • Decision Making Under Uncertainty, the Value of Information • Optimization Under Uncertainty I: Two-Stage Stochastic Programming • Optimization Under Uncertainty II: Chance-Constrained Programming • Machine Learning for Algorithm Selection • Algorithm Configuration Home Assignments: • A new set of tasks (including formulating and implementing mathematical optimization models, writing and executing python code for simple machine learning tasks, etc) will be assigned each week for students to work on independently at home. • These homework tasks are not mandatory, but students are strongly encouraged to attempt them. • During the exercise sessions, selected homework problems will be discussed and solved collaboratively. • Students who present solutions (oral presentation) to homework problems during these sessions will earn bonus points. In the Exam students will be required to: • Provide the mathematical formulation of given problems. • Write the pseudocode for the solution of some tasks. • Answer conceptual questions related to the course content.
Learning outcomes
By the end of the course, students will be able to analyze and solve complex decision-making and optimization problems under uncertainty. They will be capable of selecting, combining, and adapting appropriate methods from Operations Research, Data Science, and Machine Learning. Additionally, they will be able to identify, evaluate, and apply suitable optimization algorithms to real-world problem settings.
Assessment
• written exam, 90 min. 100% exam + bonus points (maximum 10% of the final grade and only valid after passing the exam)
Literature (3)
- Santos, H.G., Toffolo, T.A.M., Silva, R.M., & Resende, M.G.C. Mixed Integer Linear Programming with Python. Retrieved from https://app.readthedocs.org/projects/python-mip/downloads/pdf/latest/
- Birge, J.R., & Louveaux, F. (1999). An introductory tutorial on stochastic linear programming models. Interfaces, 29(2), 33–44. https://doi.org/10.1287/inte.29.2.33
- Hutter, F., Kotthoff, L., & Vanschoren, J. (2018). Model evaluation, model selection, and algorithm selection in machine learning. arXiv preprint arXiv:1811.12808. Retrieved from https://arxiv.org/pdf/1811.12808
Remarks
Home Assignments: • A new set of tasks (including formulating and implementing mathematical optimization models, writing and executing python code for simple machine learning tasks, etc) will be assigned each week for students to work on independently at home. • These homework tasks are not mandatory, but students are strongly encouraged to attempt them. • During the exercise sessions, selected homework problems will be discussed and solved collaboratively. • Students who present solutions (oral presentation) to homework problems during these sessions will earn bonus points. These bonus points will be added to the final grade, but only if the student passes the final exam
Source: BTU's module description · retrieved 29 Sep 2026Original