Machine Learning in Sociodemographic Segmentation of a Telco Company Customers
Strojové učení v sociodemografické segmentaci zákazníků telekomunikační společnosti
Authors
Supervisors
Reviewers
Editors
Other contributors
Journal Title
Journal ISSN
Volume Title
Publisher
České vysoké učení technické v Praze
Czech Technical University in Prague
Czech Technical University in Prague
Date
Abstract
Táto práca sa zaoberá použitím algoritmov strojového učenia na klasifikáciu veku a pohlavia u zákaznikov telekomunikačnej spoločnosti. Analyzuje už existujúci predikčný model a semantickú kvalitu dát, ktorej sa to týka. Boli ukázané rozdiely vo výkonnosti a rýchlosti dvoch algoritmov strojového učenia. Ďalej sa v práci experimentuje s využitím neuronových sietí na predikciu veku a pohlavia s úplne iným typom dat, aký bol použitý pri vytváraní dvoch predikčných modelov založených na algoritmoch strojového učenia.
This thesis is concerned with machine learning algorithms in order to classify the age and gender of Telco company customers. It provides the analysis of already existing predictive models and of the semantic quality of data, which were used in the training of this model. Differences in speed and performance were shown between two machine learning algorithms. Furthermore this thesis experiments with using neural network in order to predict age and gender with different types of data, than the ones used for creating the two machine learning models used for trainings.
This thesis is concerned with machine learning algorithms in order to classify the age and gender of Telco company customers. It provides the analysis of already existing predictive models and of the semantic quality of data, which were used in the training of this model. Differences in speed and performance were shown between two machine learning algorithms. Furthermore this thesis experiments with using neural network in order to predict age and gender with different types of data, than the ones used for creating the two machine learning models used for trainings.