Title :
A modular artificial neural network valuation system
Author :
Panayiotou, Panayiotis A. ; Pattichis, Constantinos ; Jenkins, David ; Plimmer, Frances
Author_Institution :
Dept. of Lands & Surveys, Land Inf. Centre, Lefkosia, Cyprus
Abstract :
The objective of this study was to design, develop and test a modular artificial neural network valuation system (MANN) incorporating multiple regression analysis (MRA) for the assessment of houses and apartments in Strovolos municipality in Cyprus for taxation purposes. The system combined the assessment results of three neural network assessors: (i) back-propagation (BP), (ii) probabilistic network (PNN) (iii) self-organising feature map (SOFM); and (iv) MRA. Features include age, size, plot size, date of sale etc. The mean absolute percentage error (MAPE) and the coefficient of dispersion (COD) of the MANN system for houses were 10.67% and 10.57% respectively. The MAPE and the COD for apartments were 8.68% and 8.41% respectively. These findings compare favourably with other studies and satisfy International Association of Assessing Officers (IAAO) criteria for mass appraisal techniques.
Keywords :
backpropagation; government data processing; neural nets; real estate data processing; statistical analysis; BP; COD; Cyprus; IAAO criteria; International Association of Assessing Officers; MANN; MAPE; MRA; PNN; SOFM; Strovolos municipality; back-propagation; backpropagation; dispersion coefficient; mass appraisal techniques; mean absolute percentage error; modular artificial neural network valuation system; multiple regression analysis; plot size; probabilistic network; sale date; self-organising feature map; taxation; Appraisal; Artificial neural networks; Computer science; Cost accounting; Marketing and sales; Neural networks; Regression analysis; Statistical analysis; Statistics; System testing;
Conference_Titel :
Electrotechnical Conference, 2000. MELECON 2000. 10th Mediterranean
Print_ISBN :
0-7803-6290-X
DOI :
10.1109/MELCON.2000.879969
