The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON COMPUTERS
Transactions ID Number: 88-355
Full Name: Petr Hajek
Position: Doctor (Researcher)
Age: ON
Sex: Male
Address: Studentska 84, Pardubice
Country: CZECH REPUBLIC
Tel: +420 466 036 004
Tel prefix: +420
Fax: +420 466 036 010
E-mail address: petr.hajek@upce.cz
Other E-mails: vladimir.olej@upce.cz
Title of the Paper: Municipal Revenue Prediction by Ensembles of Neural Networks and Support Vector Machines
Authors as they appear in the Paper: Petr Hajek, Vladimir Olej
Email addresses of all the authors: petr.hajek@upce.cz, vladimir.olej@upce.cz
Number of paper pages: 10
Abstract: Municipalities have to to pay increasing attention to the importance of revenue prediction due to fiscal stress. Currently, judgmental, extrapolative, and deterministic models are used for municipal revenue prediction. In this paper we present the designs of neural network and support vector machine ensembles for a real-world regression problem, i.e. prediction of municipal revenue. Base learners, as well as linear regression models are used as benchmark methods. We prove that there is no single ensemble method suitable for this regression problem. However, the ensembles of support vector machines and neural networks outperformed the base learners and linear regression models significantly.
Keywords: Municipal revenue, prediction, regression, support vector machine ensembles, modelling, neural network ensembles.
EXTENSION of the file: .doc
Special (Invited) Session: Municipal Revenue Prediction by Support Vector Machine Ensembles
Organizer of the Session: 646-384
How Did you learn about congress:
IP ADDRESS: 195.113.127.240
