Analýza reálných dat pro úsek zákaznických služeb

The goal of this bachelor thesis is to find certain relationships by analyzing real CRM data. These relationships would then be used to specify a draft of content of companys new webside. The analysis will be completed through CF-Miner and KL-Miner procedures, which are procedures of LISp-Miner system, which is an academic system for Knowledge Discovery in Databases, based on the GUHA method. The whole analysis process is divided according to the phases of the CRISP-DM methodology. The contribution of this thesis is primarily to find unknown relationships and dependencies, which will be effectively used in real life, along with the introduction of methods and techniques used in the analysis, and last, but not least, the introduction of LISp-Miner system itself. The thesis is divided into a theoretical and empirical sections. In the first three chapters, I will explain what is meant by Knowledge Discovery in Databases and what techniques, methodologies and procedures are used during this process. Further, I will explain individual phases of KDD corresponding to the CRISP-DM methodology. Towards the end of the theoretical part, I will describe LISp-Miner system that has been used for this analysis. The empirical section is divided according to the CRISP-DM methodology, where I will first introduce the scope and the data that will be analyzed. In further steps, I will prepare the analyzed data and use them to solve analytical problems. At the end of the empirical part, I will interpret the results of individual analyses and suggest use in real life.