Title: Real estate valuation with artificial intelligence approaches

Authors: E. Pagourtzi, K. Metaxiotis, K. Nikolopoulos, K. Giannelos, V. Assimakopoulos

Addresses: School of Electrical and Computer Engineering, Forecasting Systems Unit, National Technical University of Athens, 9, Iroon Polytechniou Str., 15773 Zografou Athens, Greece. ' Secretary for the Information Society, Ministry of Economy and Finance, 5, 7 Nikis Str., 10180, Athens, Greece. ' Lancaster Centre for Forecasting, Department of Management Science, Lancaster University Management School, Lancaster LA1 4YX, UK. ' School of Electrical and Computer Engineering, Forecasting Systems Unit, National Technical University of Athens, 9, Iroon Polytechniou Str., 15773 Zografou Athens, Greece. ' School of Electrical and Computer Engineering, Forecasting Systems Unit, National Technical University of Athens, 9, Iroon Polytechniou Str., 15773 Zografou Athens, Greece; Secretary for the Information Society, Ministry of Economy and Finance, 5, 7 Nikis Str., 10180, Athens, Greece

Abstract: Real Estate valuation in urban areas is a very difficult task that has absorbed the interest of many academics in the past years. Many qualitative and quantitative variables affect the value of an estate in urban areas. As a result, multivariate models are more suitable in the appraisal process. One of the most common approaches is multiple linear regression technique (MLR) that is always used as a benchmark in various studies. A very promising way of dealing with uncertainty in real estate analysis and producing sufficient evaluations is the use of Artificial Neural Networks (ANNs). Also, an expert method combining the strengths of MLR and ANN is tried out successfully. The purpose of this study is to compare these approaches on the basis of the data from the Attica urban area in Greece.

Keywords: real estate valuation; evaluation; urban areas; multiple linear regression; artificial neural networks; intelligent systems; Greece.

DOI: 10.1504/IJISTA.2007.011573

International Journal of Intelligent Systems Technologies and Applications, 2007 Vol.2 No.1, pp.50 - 57

Published online: 02 Dec 2006 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article