-
B323/1
Gyimesi András, Dr. Kehl Dániel, Dr. Kruzslicz Ferenc, PTE /KTK.
Topic: Association rule mining and Market Basket Analysis.
In this session the concept of association rules data mining tools is discussed, which is a form of local-pattern discovery in an unsupervised learning system. Association rules are used to uncover relationships between inherently unrelated data items. We mention and explain some of the most well-known algorithms and measures (support, lift, confidence). Different possible visualisation and implementation tools are shown. MBA is used for retail data analysis to explore customer purchasing patterns. We show an application on data of a major Hungarian fuel company. We also show how the outputs can be represented as networks and analysed this way.