Humboldt-Universität zu Berlin - School of Business and Economics

General Information

Course description

The students gain a foundational understanding of key approaches in Statistical and Machine Learning, including linear regression, regularization, Bayesian methods, exemplar and kernel methods, random trees and forests, ensemble techniques, bootstrap, boosting, unsupervised and semi-supervised learning, (re)sampling methods, and neural networks. The course primarily focuses on developing an understanding of the core concepts of supervised and unsupervised learning, as well as the links between statistical and machine learning paradigms. Students learn the theoretical properties of the main algorithms and acquire the ability to apply them to real data in practice.

Lecture: Selected topics in statistical and machine learning, e.g. linear regression, regularisation, Bayesian methods, exemplar and kernel methods, random trees and forests, ensemble techniques, bootstrap, boosting, unsupervised and semi-supervised learning, (re)sampling methods, and neural networks.

Exercise: Implementation and evaluation of selected statistical and machine learning models using statistical programming languages and modern machine learning frameworks.

Preconditions: Statistic/Econometrics, Datenanalyse or equivalent knowledge is recommended.