A Comparative Perspective on Urban Spatial Housing Market Structure: Some More Evidence of Local Sub-markets Based on a Neural Network Classification of Amsterdam

摘要: When analysing the spatial housing market structure of urban areas, a frequently arising question concerns relevant criteria for segmentation: is it transaction price or related to other, socioeconomic, demographic and physical features location? In this study, two neural network techniques (SOM, LVQ, Kohonen) are used identifying sub-markets within Amsterdam, The Netherlands. Because inductive nature modelling, any theory has be understood in an open sense: generalising principles classification another context enable elaboration institutionally sensitive theory. These findings therefore compared with earlier from market-namely, Helsinki, Finland. comparison shows that, while alone insufficient criterion both markets, Amsterdam more fragmented than Helsinki.