Using machine learning to identify spatial market segments. A reproducible study of major Spanish markets

Rey-Blanco, David; Arbués, Pelayo; Hernández, Fernando A. López; Páez, Antonio

doi:10.1177/23998083231166952

Cited by 3 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data are openly available from Idealista for Madrid, Valencia, and Barcelona (2018), and it can be accessed in reference [41]. The data include 94,814 listings posted on Idealista for the city of Madrid; we exclude 19,011 listings which remain in the portal over 4 months and are repeated in the dataset, leaving 75,803 properties.…”

Section: Housing Listings Datamentioning

confidence: 99%

Extracting Features from Satellite Imagery to Understand the Size and Scale of Housing Sub-Markets in Madrid

Kenyon,

Arribas-Bel,

Robinson

2024

Land

View full text Add to dashboard Cite

The following paper proposes a novel machine learning approach to the segmentation of urban housing markets. We extract features from globally available satellite imagery using an unsupervised machine learning model called MOSAIKS, and apply a k-means clustering algorithm to the extracted features to identify sub-markets at multiple intra-urban scales within a case study of Madrid (Spain). To systematically explore scale effects on the resulting clusters, the analysis is repeated with varying sizes of satellite image patches. We assess the resulting clusters across scales using several internal cluster-evaluation metrics. Additionally, we use data from online listings portal Idealista to measure the homogeneity of housing prices within the clusters, to understand how well sub-markets can be differentiated by the image features. This paper evaluates the strengths and weakness of the method to identify urban housing sub-markets, a task which is important for planners and policy makers and is often limited by a lack of data. We conclude that the approach seems useful to divide large urban housing markets according to different attributes and scales.

show abstract

Section: Housing Listings Datamentioning

confidence: 99%

Extracting Features from Satellite Imagery to Understand the Size and Scale of Housing Sub-Markets in Madrid

Kenyon,

Arribas-Bel,

Robinson

2024

Land

View full text Add to dashboard Cite

show abstract

“…However, to comply with data legislation, we have masked the prices by applying a small amount of random noise that will not bias the main results derived from its usage. This micro-data set can be used to benchmark new methods in a reproducible fashion (e.g., Rey-Blanco et al, 2024). Applied and theoretical researchers on real estate mass appraisal and valuation methods might use this data set to canonically compare the performance of their proposed comparable and hedonic models, among others.…”

Section: Introductionmentioning

confidence: 99%

“…This micro-data set can be used to benchmark new methods in a reproducible fashion (e.g., Rey-Blanco et al, 2024). Applied and theoretical researchers on real estate mass appraisal and valuation methods might use this data set to canonically compare the performance of their proposed comparable and hedonic models, among others.…”

Section: Introductionmentioning

confidence: 99%

A geo-referenced micro-data set of real estate listings for Spain’s three largest cities

Rey-Blanco,

Arbues,

Lopez

et al. 2024

Environment and Planning B: Urban Analytics and City Science

Self Cite

View full text Add to dashboard Cite

This article presents an open data product with large geo-referenced micro-data sets of 2018 real estate listings in Spain. These data were originally published on the idealista.com real estate website. The observations were obtained for the three largest cities in Spain: Madrid ( n = 94,815 observations), Barcelona ( n = 61,486 observations), and Valencia ( n = 33,622 observations). The data sets include the coordinates of properties (latitude and longitude), asking prices of each listed dwelling, and several variables of indoor characteristics. The listings were enriched with official information from the Spanish cadastre (e.g., building material quality) plus other relevant geographical features, such as distance to urban points of interest. Along with the real estate listings, the data product also includes neighborhood boundaries for each city. The data product is offered as a fully documented R package and is available for scientific and educational purposes, particularly for geo-spatial studies.

show abstract

Prototype-based learning for real estate valuation: a machine learning model that explains prices

Rodriguez-Serrano

2024

Ann Oper Res

View full text Add to dashboard Cite

The systematic prediction of real estate prices is a foundational block in the operations of many firms and has individual, societal and policy implications. In the past, a vast amount of works have used common statistical models such as ordinary least squares or machine learning approaches. While these approaches yield good predictive accuracy, most models work very differently from the human intuition in understanding real estate prices. Usually, humans apply a criterion known as “direct comparison”, whereby the property to be valued is explicitly compared with similar properties. This trait is frequently ignored when applying machine learning to real estate valuation. In this article, we propose a model based on a methodology called prototype-based learning, that to our knowledge has never been applied to real estate valuation. The model has four crucial characteristics: (a) it is able to capture non-linear relations between price and the input variables, (b) it is a parametric model able to optimize any loss function of interest, (c) it has some degree of explainability, and, more importantly, (d) it encodes the notion of direct comparison. None of the past approaches for real estate prediction comply with these four characteristics simultaneously. The experimental validation indicates that, in terms of predictive accuracy, the proposed model is better or on par to other machine learning based approaches. An interesting advantage of this method is the ability to summarize a dataset of real estate prices into a few “prototypes”, a set of the most representative properties.

show abstract

Using machine learning to identify spatial market segments. A reproducible study of major Spanish markets

Cited by 3 publications

References 49 publications

Extracting Features from Satellite Imagery to Understand the Size and Scale of Housing Sub-Markets in Madrid

Extracting Features from Satellite Imagery to Understand the Size and Scale of Housing Sub-Markets in Madrid

A geo-referenced micro-data set of real estate listings for Spain’s three largest cities

Prototype-based learning for real estate valuation: a machine learning model that explains prices

Contact Info

Product

Resources

About