Data Science describes a set of methods and processes for extracting knowledge from large data sets. This module introduces the process of data science, gives an overview on the different methods for every stage and their application in different application scenarios. In the exercise, students apply those methods on example data sets.
The course emphasizes practical over theoretical aspects and a more programmatic approach, rather than a mathematical one.

Topics :
• Data science: history and background
• The Knowledge Discovery Process: data gathering, feature engineering, data mining, machine learning and visualizations, discovery, exploration, testing and evaluation
• Descriptive Statistics and Univariate/Bivariate Visualisations
• Feature Engineering: feature selection, feature transformation, dimensionality reduction
• Selected Supervised and Unsupervised Machine Learning Models (e.g. Decistion Trees, Neural Networks, Probabilistic Classifiers, Clustering)
• Selected application domains: Recommendation engine; Fraud detection; Simulators, Forecasting and Classification; Social Network Analysis, Text Mining
• Current trends

Kenntnisse/ Knowledge:

The students gain a very good understanding of a set of methods and processes for extracting knowledge from large data sets.

Fähigkeiten/Skills:

The students understand the foundations of data science and are able to apply them in big data settings. Students are also able to apply techniques for extracting knowledge from data and to self-learn data science methods not taught in the course.

Kompetenzen/ Competences:

The students became familiar with large-scale data analysis in different applications. They have the ability to select methods best suited for particular application settings.