Analysis of the Prague used car market using data mining methods

This bachelor's thesis aims to obtain data using web scraping technology and subsequent analysis of this data using exploratory analysis and data mining techniques to identify interesting patterns and trends in the Prague used car market. The work is divided into theoretical and practical parts. In the theoretical part, the field of data mining is introduced in detail, including the description of basic concepts, selected methods, their application, and evaluation methods. The CRISP-DM methodology is then described, which provides a framework for managing data mining projects and will be used in the practical part of the work. Subsequently, attention is focused on web scraping technology, its principles, tools, and ethical aspects associated with this area. In the practical part, the process of obtaining data from the online used car market tipcars.com using web scraping and their preprocessing using Excel and Python is described in detail. Based on this preprocessed data, a thorough exploratory analysis is conducted, which subsequently allows the creation of models, including a regression model and cluster analysis. Within the regression modeling, two models are created, one based on numerical attributes and the other combining numerical and categorical attributes. The cluster analysis involves the identification of four clusters, which are subsequently visualized using graphs. Before the conclusion of the work, the achieved results and findings are discussed. The conclusion contains a summary of the entire work and its important aspects.