Název:	Modelování kvality života pomocí rozhodovacích stromů
Další názvy:	Quality of life modelling based on decision trees
Autoři:	Křupka, Jiří Kašparová, Miloslava Jirava, Pavel
Citace zdrojového dokumentu:	E+M. Ekonomie a Management = Economics and Management. 2010, č. 3, s. 130-146.
Datum vydání:	2010
Nakladatel:	Technická univerzita v Liberci
Typ dokumentu:	článek article
URI:	http://www.ekonomie-management.cz/download/1331826751_3c30/11_krupka.pdf http://hdl.handle.net/11025/17360
ISSN:	1212-3609 (Print) 2336-5604 (Online)
Klíčová slova:	regionální management;rozhodovací stromy;klasifikace
Klíčová slova v dalším jazyce:	regional management;decision trees;classification
Abstrakt v dalším jazyce:	This paper presents one of the possibilities of the decision theory that can be used in the mode- lling of the quality of life in a given city in the Czech Republic. Real data sets of citizen questioners for the city of Chrudim were analysed, pre-processed, and used in the model. This model is defined as classification model and it uses algorithms used in decision trees. A decision tree is a predictive model which can be used to represent both classifiers and regre- ssion models. In operations research, a decision trees refers to a hierarchical model of decisions and their consequences. When decision tree are used as a classification tasks, it is more appro- priately referred to as a classification tree. Classification trees are used to classify an object, or an instance, to a predefined set of classes based on their attribute’s value. These trees are frequently used in applied fields such as: finance, marketing, engineering, and medicine. They are useful as an exploratory technique. There are various top-down decision trees inducers such as ID3, C4.5, and C&RT. In our case we used C5.0, C&RT, and CHAID algorithm for the modelling of the quality of life in the previously mentioned city. Similar results were achieved through out our research when using the mentioned algorithms. H owever, the best results were achieved when using the C5.0 algorithm. Finally, we summarized the presented problems, and compared its accuracy in classification on the basis of decision trees, with classification results based on the probabilistic neural network and the radial basis function neural network.
Práva:	© Technická univerzita v Liberci CC BY-NC 4.0
Vyskytuje se v kolekcích:	Číslo 3 (2010) Číslo 3 (2010)

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.