The thesis deals with pre-processing of two data sets with information on clients, loans and debit cards. The data sets were separately pre-processed and modeled by SPSS Modeler using a number of methods and algorithms. For the modeling purposes, three classification data mining tasks were defined: loan approving or rejecting, loan rating and debit card type assignment. By using the selected methods of machine learning techniques the classification models were built for each task. Models accuracy was tested by script written in SPSS language for automation. All tasks were supplemented by clustering technique based on latent factors gained by factor analysis. Factor analysis combined with clustering presents another approach in pattern discovery.
Identifer | oai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:251149 |
Date | January 2016 |
Creators | Melichar, Miloš |
Source Sets | Czech ETDs |
Language | Czech |
Detected Language | English |
Type | info:eu-repo/semantics/masterThesis |
Rights | info:eu-repo/semantics/restrictedAccess |
Page generated in 0.0109 seconds