The 11th Annual Conference of the Pacific Rim Real Estate Society January 23 to 26, 2005 The University of Melbourne Victoria, Australia Tom Kauko OTB Research Institute for Housing, Urban and Mobility Studies Delft University of Technology Jaffalaan 9 P. O. Box 5030 2600 GA Delft The Netherlands Email:
[email protected] The Budapest housing market structure from a heterodox economics perspective and with a neural network classification Abstract: The development of the housing markets in different European metropolitan areas is of high interest for the urban development and the real estate markets, which are about to globalise. What sort of pricing mechanism is able to explain the house prices in different areas? The Budapest housing market is well-suited for scrutiny from an institutional and evolutionary perspective. The housing market is very fragmented with respect to location; several different house types, age-categories and price-levels, as well as micro-locations, are to be found side by side. It is an extremely patchy and multi-faceted setting, and running the data with neural network modelling techniques, namely the self-organizing map (the SOM) and the learning vector quantification (the LVQ), together with conducting the conceptual level analysis using a heterodox economics framework and some qualitative material, sheds some light about the systematic to the degree the market is affected by physical and socio- demographic characteristics, price and regulation. Keywords: Budapest, Housing, Pricing Mechanism, Neural Networks. 1 The Budapest housing market structure from a heterodox economics perspective and with a neural network classification 1. Introduction As global economic functions are increasingly articulated at a local level, today territorial competition cannot be understood as a process that is contained within national boundaries.