Comparison of selected classification methods based on real datasets

This bachelor thesis deals with the comparison of selected classification methods based on real datasets. The aim of the thesis is to evaluate the performance of the selected classification methods: logistic regression, decision tree, random forest and support vector machine. The theoretical part of the thesis presents the methods and the techniques used to evaluate the models. In the practical part, five real datasets are worked with. This part includes the description of the datasets, performing exploratory data analysis, selecting relevant variables and building and evaluating the models. Finally, the results are interpreted with respect to different performance metrics and the appropriateness of using each method in specific situations is discussed.