Capturing Housing Market Segmentation: An Alternative Approach based on Neural Network Modelling

Kauko, Tom; Hooimeijer, Pieter; Hakfoort, Jacco

doi:10.1080/02673030215999

Cited by 101 publications

(77 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to save space, sections 3 and 4 cover the Dutch and the Hungarian analyses only, as the Finnish analysis has already been presented in earlier work (see Kauko, 2002;Kauko et al, 2002). Each section begins with an outline of the spatial housing market structure of urban areas in the specific country context in order to provide some background information, followed by an examination of the SOM output.…”

Section: Developing a Methods Based On The Kohonen Mapmentioning

confidence: 99%

See 1 more Smart Citation

Using the Self-Organising Map to Identify Regularities across Country-Specific Housing-Market Contexts

Kauko¹

2005

Environ Plann B Plann Des

Self Cite

View full text Add to dashboard Cite

The aim to explore and monitor housing-market fundamentals (prices, dwelling features, area density, residents, etc) at a macrolocational level is motivated by various policy-related and business-related goals (for example, see Tu, 2000). Housing-market segmentation (that is, the emergence of housing submarkets), a concept with increasing relevance, relates to the differentiation of housing through the income and preferences of residents and in terms of administrative circumstances. The causes of segmentation processes pertain to a multitude of impacts related to geographical location (including topographical constraints), structural (that is, house-specific and site-specific) attributes, prices, consumer preferences and incomes, government regulation, and asymmetric information and power positions between market participants (for example, see Watkins, 2001). The monitoring of segmentation has various practical implications when a comparative evaluation of attractiveness is required.However, the research problem of determining segments and tracking the processes behind segmentation has also received attention as a purely academic endeavour within housing economics. According to Maclennan and Tu (1996), submarkets are the product of market imperfections in relation to local-level supply-and-demand structures. Thus, differentiation of preferences and product groups, trade friction and search processes lead to a complexity and variety in the housing commodity; furthermore, any equilibrium tends to be unstable, in the short term at least. Although depending on the exact definitions used, in any one housing-market context segments are likely to occur over time and space, which implies that the verification of segmentation is predominantly an empirical issue. Although a national housing market is Using the self-organising map to identify regularities across country-specific housing-market contexts Abstract. The aim of exploring and monitoring housing-market fundamentals (prices, dwelling features, area density, residents, and so on) on a macrolocational level relates to both public and private sector policymaking. Housing market segmentation (that is, the emergence of housing submarkets), a concept with increasing relevance, is defined as the differentiation of housing in terms of the income and preferences of the residents and in terms of administrative circumstances. In order to capture such segmentation empirically, the author applies a fairly new and emerging technique known as the`selforganising' map (SOM), or`Kohonen map'. The SOM is a type of (artificial) neural network öa nonlinear and flexible (that is, nonparametric or semiparametric) regression and`machine learning' technique. By utilising the ability of the SOM to visualise patterns, one can analyse various dimensions within the variation of the dataset. Segmentation may then be detected depending on the resulting patterns across the map layers, each of which represents the data variation for one input variable. Utilising an inductive modelling strategy, t...

show abstract

Section: Developing a Methods Based On The Kohonen Mapmentioning

confidence: 99%

“…Elsewhere, I have demonstrated the use of the SOM-based method, with one city as an exemplar (see Kauko, 2002;Kauko et al, 2002). Here, the aim is to apply nationwide datasets.…”

Section: Geographically Extended Housing-market Analysismentioning

confidence: 99%

Using the Self-Organising Map to Identify Regularities across Country-Specific Housing-Market Contexts

Kauko¹

2005

Environ Plann B Plann Des

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are mainly two theoretical perspectives on the real estate market segmentation in previous literature, which are segmentation based on factors influencing consumers' housing preferences and segmentation based on real estate market performance [5,6]. The first is a long-term perspective that emphasizes on classifying the real estate market into submarkets according to key factors that influence the market.…”

Section: Idi = 2covar(inve Rank Inve )mentioning

confidence: 99%

Segmentation of Chinese Urban Real Estate Market: A Demand-Supply Distribution Perspective

Dong

et al. 2015

Ann. Data. Sci.

View full text Add to dashboard Cite

This study proposed a new perspective on the analysis of the regional features of real estate market and explored a more reliable segmentation method for Chinese urban real estate market based on the optimization of supply-demand resource distribution. A two-stage clustering procedure is proposed based on supply and demand elements and market performance respectively. And six clustering algorithms were used to divide 283 Chinese cities at the prefecture level or above into three clusters and 13 sub-clusters, which are identified as key regulatory region, stable development region and region that needs policy support. Differentiated regulatory policy suggestions are accordingly provided for each cluster.

show abstract

“…[6] explore the more effective method of market segmentation on the basis of continuous improvement of information processing and communication technology, and elaborates the feasibility of neural network model in detail. Kauko, T. [7] uses two kinds of neural network model -self-organizing map (SOM) and learning vector quantization (LVQ) model of Finland Helsinki's real estate market segmentation and finds that customers are more concerned about the geographical location and housing types, and house prices are less considered factors. Derrick S. Bullone and Michelle Roehm [8] apply fuzzy artificial neural network analysis technology to test membership clustering criteria, based on the existing method to determine the target market segmentation, and verify the advantages of different market segments.…”

Section: Customer Segmentation Based On Data Sciencementioning

confidence: 99%

Research on the Application Development of Data Science in Customer Segmentation

Xu¹

2017

Proceedings of the 2017 3rd International Conference on Economics, Social Science, Arts, Education and Management Engineering (

View full text Add to dashboard Cite

Abstract. Data science is an emerging discipline that extracts knowledge from data, and is formally put forward in the context of the "fourth paradigm" of scientific research. The data used for business decision-making and scientific research have radically changed, characterized by the original mainstream sampling, structured, small-scale development to full data, semi-structured and unstructured, large-scale, driven data science developed into both Including traditional statistical methods, but also includes data mining, text mining, process mining and large data and other emerging technologies interdisciplinary. Customer segmentation is a typical data oriented business and research areas, data science in one of the application shows that the subject contains a variety of methods, can successfully extract complex customer related data contains information and knowledge, can solve the problem of the feasibility and effectiveness of customer segmentation, accuracy, and business practices for customer segmentation study provides good technology support and decision support.

show abstract

Capturing Housing Market Segmentation: An Alternative Approach based on Neural Network Modelling

Cited by 101 publications

References 19 publications

Using the Self-Organising Map to Identify Regularities across Country-Specific Housing-Market Contexts

Using the Self-Organising Map to Identify Regularities across Country-Specific Housing-Market Contexts

Segmentation of Chinese Urban Real Estate Market: A Demand-Supply Distribution Perspective

Research on the Application Development of Data Science in Customer Segmentation

Contact Info

Product

Resources

About