Numerical prediction, endogeneity and generalized linear models, logistic regression, naive bayes, decision tree learners, data preparation, evaluation of classifiers, ensemble methods, clustering algorithms, association rule mining.

Learning outcomes

After successful completion of the module, students know central methods used for data analysis. The course focuses on applications in business, most notably on marketing applications. They understand the theoretical foundation of discrete choice models and selected machine learning methods. Students are able to analyze data sets and solve classification problems, perform forecasting, and clustering tasks. Moreover, students know about the assumptions, the advantages and disadvantages of different methods and know properties of respective algorithms. Attending the voluntary computer tutorial, students are able to analyze data in a programming software like R.
Number of credit hours per week 3