Supervised Machine Learning: RegressionModule description #70370 / Version 3
- 6 CP
- Written exam
- Graded
- Summer semester
- English
This module description is not valid in the current semester (Winter semester 2026/27).
Current version (v4)
| Module / Version | #70370 / #3 |
|---|---|
| Validity | Summer semester 2025 – Summer semester 2025 |
| Available language(s) | English, German |
| Credit points | 6 |
| Person responsible for the module | Werwatz, Axel |
| Grading | Graded |
| Exam format | Written exam |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät VII |
|---|---|
| Institute | Institut für Volkswirtschaftslehre und Wirtschaftsrecht |
| Academic chair | 37312100 FG Ökonometrie und Wirtschaftsstatistik |
Contact
| Office | H 57 |
|---|---|
| Contact person | Marcath, Ronja Maria |
| E-mail address | sekretariat@statistik.tu-berlin.de |
| Website | http://www.statistik.tu-berlin.de |
Learning outcomes
Learning Outcomes
Regression is a key tool for empirical academic research for explanation, i.e. estimating, causal relationships between variables. Recently, it has taken center stage as a key tool for prediction, i.e. supervised statistical learning with a continuous target variable Y. This will be the perspective of this class. The empirical example, used throughout this course, will be the predicition of house prices (Y) given its characteristics (X).
In the lectures of this course, students will gain knowledge on the theoretical concepts of forecasting in the context of regression analysis. In the tutorials, this knowledge will be used to actually implement and estimate empirical prediction models using the programming language Python. This will enable students to autonomously answer empirical research questions. This encompasses the specification of statistical models as well as their estimation. Theoretical knowledge from the lectures endows students to contextualize the obtained results. This includes the recognition of falsely specified models as well as the correct interpretation of model results. Furthermore, students will gain an expertise in the processing of empirical research projects typically part of a scientific thesis. Having prior knowledge in Python programming is recommended.
Regression is a key tool for empirical academic research for explanation, i.e. estimating, causal relationships between variables. Recently, it has taken center stage as a key tool for prediction, i.e. supervised statistical learning with a continuous target variable Y. This will be the perspective of this class. The empirical example, used throughout this course, will be the predicition of house prices (Y) given its characteristics (X).
In the lectures of this course, students will gain knowledge on the theoretical concepts of forecasting in the context of regression analysis. In the tutorials, this knowledge will be used to actually implement and estimate empirical prediction models using the programming language Python. This will enable students to autonomously answer empirical research questions. This encompasses the specification of statistical models as well as their estimation. Theoretical knowledge from the lectures endows students to contextualize the obtained results. This includes the recognition of falsely specified models as well as the correct interpretation of model results. Furthermore, students will gain an expertise in the processing of empirical research projects typically part of a scientific thesis. Having prior knowledge in Python programming is recommended.
Content
• Loss Functions and Optimal Prediction
• Model Selection (bias-variance trade-off, cross-validation, information criteria)
• Nonparametric kernel regression
• Nearest-neighbor regression
• Generalized additive Models
• Least squares and multiple linear regression
• Ridge, LASSO and Elastic Net regression
• Regression trees
• Support vector machines
• Model Selection (bias-variance trade-off, cross-validation, information criteria)
• Nonparametric kernel regression
• Nearest-neighbor regression
• Generalized additive Models
• Least squares and multiple linear regression
• Ridge, LASSO and Elastic Net regression
• Regression trees
• Support vector machines
Module components
Compulsory area
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| Supervised Machine Learning: Regression | Lecture | VL 71 21 L | Winter semester | [en] | 2 | WS 2026/27 (1) ISIS |
| Supervised Machine Learning: Regression | Exercise | VL 71 21 L | Winter semester | [en] | 2 | WS 2026/27 (1) ISIS |
Courses in the course catalog
Courses created from the teaching units of this module.
Winter semester 2026/27 (2)
Supervised Machine Learning: Regression (Lecture) 1
- Supervised Machine Learning: Regression (Vorlesung) Termingruppe 1 VL 71 21 L
Supervised Machine Learning: Regression (Exercise) 1
- Supervised Machine Learning: Regression (Übung) Termingruppe 1 VL 71 21 L
Workload and credit points
Supervised Machine Learning: Regression (Lecture)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre-/Post-processing | 15 | 2 h | 30 h |
| 60 h | |||
Supervised Machine Learning: Regression (Exercise)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre-/Post-processing | 15 | 2 h | 30 h |
| 60 h | |||
Course-independent workload
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Examination preparation | 1 | 60 h | 60 h |
| 60 h | |||
The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
Lecture (VL) and computer-aided tutorial (UE). Tutorials will make use of interactive tools for statistical programming. There will be programming and data analysis assignments using statistical programming with python.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Knowledge of probability theory and statistical inference at the level of „Statistik I für Ökonomen und Wirtschaftsingenieure“ and „Statistik II für Ökonomen und Wirtschaftsingenieure“. A class in regression analysis such as „Ökonometrie“ is desireable.
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Written exam |
| Language | English |
| Duration/Extent | 90 min |
Duration of the module
The following number of semesters is estimated for taking and completing the module: 1 semester(s).
This module can be started in the following semesters: Summer semester.
Maximum number of participants
This module is not limited to a number of students.
Registration procedures
Participation in this module does not require registration.
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
unavailable
Recommended literature
- Fahrmeir, L., Kneib, T., Lang, S., Regression, Springer.
- Hastie, T., Tibshirani, R. and Friedman, J. (2017). The elements of statistical learning. 2nd edition. Corrected 12th printing, Springer Series in Statistics.
Assigned programs
This module version is used in the following programs:
| Program / program version | Semester(s) | Curriculum component |
|---|---|---|
| Economics and Sustainability StuPO 2024 | SS 2025 | Wahlpflichtbereich „Economics, Sustainability and Technology“ › Economic Sustainability |
| Industrial Economics StuPO 2018 | SS 2025 | Compulsory Elective Modules › Field Courses › Field Courses |
| Industrial Engineering and Management Industrial Engineering and Management (M. Sc.) - StuPO 2015 | SS 2025 | Integrationsbereich/Integration › Integrationsbereich/Integration (Wahlpflicht/Compulsory-Elective) › Statistics & Econometrics |
Not specified
Miscellaneous
The class will be taught in English.