Academic literature on the topic 'Spatial Hedonic Prices Method'

Abstract Location is capitalized into the price of the land the structure of a property is built on, and land prices can be expected to vary significantly across space. We account for spatial variation of land prices in hedonic house price models using geospatial data and a semi-parametric method known as mixed geographically weighted regression. To measure the impact on aggregate price change, quality-adjusted (hedonic imputation) house price indices are constructed for a small city in the Netherlands and compared to price indices based on more restrictive models, using postcode dummy variables, or no location information at all. We find that, while taking spatial variation of land prices into account improves the model performance, the Fisher house price indices based on the different hedonic models are almost identical. The land and structures price indices, on the other hand, are sensitive to the treatment of location.

The main purpose of this paper is to use regression models to explore the factors affecting housing prices as well as apply spatial aggregation to explore the changes of urban space prices. This study collected data in Taitung City from the year 2013 to 2017, including 3533 real estate transaction price records. The hedonic price method, spatial lag model and spatial error model were used to conduct global spatial self-correlation tests to explore the performance of house price variables and space price aggregation. We compare the three models by R² and Akaike Information Criterion (AIC) to determine the spatial self-correlation ability performance, and explore the spatial distribution of prices and the changes of price regions from the regional local indicators of spatial association spatial distribution map. Actual analysis results show an improvement in the ability to interpret real estate prices through the feature price mode from the R² value assessment, the spatial delay model and the spatial error model. Performance from the AIC values show that the difference of the spatial delay model is smaller than that of the feature price model and the spatial model, demonstrating a better performance from the space delay model and the spatial error model compared to the feature price model; improving upon the estimation bias caused by spatial self-correlation. For variables affecting house pricing, research results show that Moran’s I is more than 0 in real estate price analysis over the years, all of which show spatial positive correlation. From the LISA analysis of the spatial aggregation phenomenon, we see real estate prices rise in spaces surrounded by high-priced real estate contrast with the scope of space surrounded by low-cost real estate shifting in boundary over the years due to changes in the location and attributes of real estate trading transactions. Through the analysis of space price aggregation characteristics, we are able to observe the trajectory of urban development.

This study evaluates the ability of a range of popular aggregate house price indexes to predict house prices out-of- sample at the transaction level for a small geographic area. The analysis particularly addresses the utility of spatial econometric methods. The results suggest that spatial econometric methods, which more explicitly consider the spatial aspects of observed house prices, provide better predictive accuracy as compared to more traditional estimation techniques, such as the repeat sales index, a hybrid repeat sales-hedonic price index, and hedonic price models estimated through least squares. The conclusions are drawn from a sample of 38,984 single-family residential real estate transactions for the city of Milwaukee, Wisconsin over the years 2002-2008.

The study aimed to determine the influence of the proximity of Wielkopolski National Park (WNP) on the value of dwelling units in Mosina municipality. The research was conducted based on 1182 residential property transactions in the period from 2014 to 2018. The input data were subjected to spatial and statistical analysis. The main part of the analysis was performed with the use of the hedonic price method (HPM)—WLS (weighted least squares). The use of statistical tools made it possible to find undeniable evidence that the housing prices are positively related to the presence of Wielkopolski National Park, which has also been confirmed by previous research works conducted in other parts of the world.

Different valuation methods and determinants of housing prices in Budapest, Hungary are examined in this paper in order to describe price drivers by using an asking price dataset. The hedonic regression analysis and the valuation method of the artificial neural network are utilised and compared using both technical and spatial variables. In our analyses, we conclude that according to our sample from the Budapest real estate market, the Multi-Layer Preceptron (MLP) neural network is a better alternative for market price prediction than hedonic regression in all observed cases. To our knowledge, the estimation of housing price drivers based on a large-scale sample has never been explored before in Budapest or any other city in Hungary in detail; moreover, it is one of the first papers in this topic in the CEE region. The results of this paper lead to promising directions for the development of Hungarian real estate price statistics.

Hedonic pricing is an indirect valuation method that applies to heterogeneous goods investigating the relationship between the prices of tradable goods and their attributes. It can be used to measure the value of irrigation water through the estimation of the model that describes the relation between the market value of the land parcels and its characteristics. Because many of the land parcels included in a hedonic pricing model are spatial in nature, the conventional regression analysis fails to incorporate all the available information. Spatial regression models can achieve more efficient estimates because they are designed to deal with the spatial dependence of the data. In this paper, the authors present the results of an application of the hedonic pricing method on irrigation water valuation obtained using a software tool that is developed for the ArcGIS environment. This tool incorporates, in the GIS application, the estimation of two different spatial regression models, the spatial lag model and the spatial error model. It also has the option for different specifications of the spatial weights matrix, giving the researcher the opportunity to examine how it affects the overall performance of the model.

This study employs the hedonic pricing method and a rich spatial and temporal dataset from two counties in Washington, USA to determine the effect of the 2009 Nisqually Restoration project (NRP) on housing prices in adjacent communities. The NRP restored 308 hectares of wetlands via dike removal in the Billy Frank Jr. Nisqually National Wildlife Refuge (NNWR), leading to improvements in salmon and bird abundance and recreational opportunities. We find that the ecological improvements made by the NRP increased the value of homes within 0.5 mile of the refuge by $37,631; homes 0.5 to 1 mile by $10,489; and homes 1 to 1.5 miles by $31,186. Our findings are consistent with previous wetland hedonic price analyses and may be useful inputs in natural resource management and policy decision-making.

This paper proposes a hedonic regression model to estimate housing prices and the spatial variability of prices over multiple years. Using the model, maps are obtained that represent areas of the city where there have been positive or negative changes in housing prices. The regression-cokriging (RCK) method is used to predict housing prices. The results are compared to the cokriging with external drift (CKED) model, also known as universal cokriging (UCK). To apply the model, heterotopic data of homes for sale at different moments in time are used. The procedure is applied to predict the spatial variability of housing prices in multi-years and to obtain isovalue maps of these variations for the city of Granada, Spain. The research is useful for the fields of urban studies, economics, real estate, real estate valuations, urban planning, and for scholars.

While urban rail transit relieves traffic pressure and improves the urban transportation network, it also has a certain impact on the prices of commercial residential properties along the line, and more and more scholars have begun to pay attention to the relationship between rail transit and real estate prices. By sorting out the relevant domestic and foreign research, the existing research results are analyzed from three aspects: research objects, research methods, and research contents, and it is found that Hedonic Price Model is most commonly adopted, and the research in the fields of spatial effect, temporal effect and sub-market effect of rail transit on real estate prices is gradually becoming a hot spot.

Purpose Numerous geo-statistical methods have been developed to analyse the spatial dimension and composition of house prices. Despite these advances, spatial filtering remains an under-researched approach within house price studies. This paper aims to examine the spatial distribution of house prices using an eigenvector spatial filtering (ESF) procedure, to analyse the local variation and spatial heterogeneity. Design/methodology/approach Using 2,664 sale transactions over the one year period Q3 2017 to Q3 2018, an eigenvector spatial filtering approach is applied to evaluate spatial patterns within the Belfast housing market. This method consists of using geographical coordinates to specify eigenvectors across geographic distance to determine a set of spatial filters. These convey spatial structures representative of different spatial scales and units. The filters are incorporated as predictors into regression analyses to alleviate spatial autocorrelation. This approach is intuitive, given that detection of autocorrelation in specific filters and within the regression residuals can be markers for exclusion or inclusion criteria. Findings The findings show both robust and effective estimator consistency and limited spatial dependency – culminating in accurately specified hedonic pricing models. The findings show that the spatial component alone explains 14.6 per cent of the variation in property value, whereas 77.6 per cent of the variation could be attributed to an interaction between the structural characteristics and the local market geography expressed by the filters. This methodological step reduced short-scale spatial dependency and residual autocorrelation resulting in increased model stability and reduced misspecification error. Originality/value Eigenvector-based spatial filtering is a less known but suitable statistical protocol that can be used to analyse house price patterns taking into account spatial autocorrelation at varying (different) spatial scales. This approach arguably provides a more insightful analysis of house prices by removing spatial autocorrelation both objectively and subjectively to produce reliable, yet understandable, regression models, which do not suffer from traditional challenges of serial dependence or spatial mis-specification. This approach offers property researchers and policymakers an intuitive but comprehensible approach for producing accurate price estimation models, which can be readily interpreted.

This dissertation consists of three papers that explore the intersection between geography and housing markets. The research examines both how geographic context shapes housing prices and how house prices influence geography through household location decisions.The first paper explores the spatial structure of housing prices within Tucson, Arizona. Hedonic house-price studies typically assume that housing attribute prices are constant over space. The research tests this assumption and compares two methods of incorporating spatial-varying parameters into house-price models: geographically weighted regression and the spatial expansion method. The results provide evidence that housing attribute prices do indeed vary with geographic context and suggest that more reliable parameter estimates and better house-price estimation accuracy can be achieved through the use of these techniques.The second paper builds upon the first by examining how more realistic conceptions of housing market spatial structure influence the hedonic price estimates of location-specific externalities. The empirical analysis examines how two key spatial effects, spatial dependence and spatial heterogeneity, impact the marginal price estimates for proximity to the Rillito River, within Tucson, Arizona. Both spatial effects are found to influence the resulting estimates, but spatial heterogeneity is of greater practical importance as the price estimates vary widely with geographic context. This research highlights the importance of considering both spatial effects in hedonic externality valuations.The final paper explores how housing prices influence interregional migration patterns, and more specifically, how their influence varies with both stage in the life course and educational attainment. The research models metropolitan migration within the United States during the period 1995 to 2000. The results indicate that housing prices play an important role in driving regional demographic change, as their influence varies with both demographic characteristics. High housing prices deter individuals in their late twenties and early thirties, but their influence wanes during middle age. House prices become more important as individuals near retirement. The results also provide evidence that college graduates respond more to house price differentials than do persons with lower levels of educational attainment.

Information asymmetry could result in sub-optimal decision making. Information asymmetry can therefore undermine the efficiency of economic activities by influencing and reducing social welfare. To overcome these inefficiencies most of the economic analyses have assumed the provision of perfect information. This is not a practical assumption and results become only partially correct. This PhD thesis analyses the effect of information asymmetry on housing market. This study examines the impact of announcements of the Western Brisbane Transport Network on nearby property prices. Negative impacts related to transport corridors are analysed including noise and air pollution and impacts on visual amenity. Also undertaken is a spatial analysis of house prices which measures the magnitude of negative impacts of corridor expansions. The study shows that buyers who were aware of the road corridor expansions experience a higher utility compared to those who were not.

Les activités économiques présentent des formes et des degrés de dépendance variables à l’environnement. L’environnement peut intervenir comme un facteur de production, comme une contrainte à l’usage de certains intrants, comme une contrainte pour certains facteurs de production. La dépendance peut être reliée à la disponibilité ou à la qualité de certaines ressources environnementales, à leur dimension de bien collectif. Il s’agira d’explorer les implications des différentes formes de dépendances bio-physico-chimiques mais aussi juridiques. Dans le cas de l’ostréiculture arcachonnaise, on examinera les formes de dépendance et leur mesure économique, à travers les impacts économiques liés à la disponibilité variable des ressources biologiques marines mais aussi à la productivité naturelle du milieu. L’analyse des caractéristiques socio-économiques des entreprises ostréicoles arcachonnaises permettra de dresser une typologie de ces dernières et ainsi caractériser l’activité. Une approche par la fonction de production sera utilisée pour mettre en évidence les degrés divers de sensibilité à une variation des conditions environnementales de production tandis que l’évaluation par la méthode des prix hédoniques permettra de déterminer le prix implicite des composantes environnementales des indemnités de substitution en tenant compte par ailleurs de la localisation géographique des concessions ostréicoles
Economic activities have forms and degrees of dependency variables to the environment. The environment can act as a factor of production as a constraint to the use of certain inputs, such as a constraint for some inputs. Dependence may be related to the availability or quality of certain environmental resources. It will explore the implications of different forms of dependencies bio-physico-chemical as well as legal. In the case of the Arcachon Bay oyster-farming will examine the forms of dependence and economic measure, through the economic impacts associated with the variable availability of living marine resources but also to the natural productivity of the environment. The analysis of socio-economic characteristics of Arcachon Bay oyster-farms will develop a typology of the latter and thus characterize the activity. A production function approach will be used to highlight the varying degrees of sensitivity to changes in environmental conditions of production while the evaluation by the hedonic price method will determine the implicit price of environmental components of the oyster leases value taking into account also the geographical location of oyster leases

The research methodology comprises theoretical, empirical and evaluation stages.  The theoretical stage provides evidence that substantiates the need for the study and outlines possible ways to address spatial elements in hedonic price modelling.  The empirical stage illustrates the application of GIS and spatial statistics in the estimation of hedonic models for housing markets in Glasgow, Scotland, using 2,715 house prices for 2002 and 61 independent variables.  GIS is used in this study to construct spatial variables including detailed accessibility measures, to help detect the hedonic problems of heteroscedasticity and spatial autocorrelation, and for visualisation.  Spatial statistics are used to test formally and model explicitly the spatial autocorrelation.  The evaluation stage assesses 46 hedonic models, using OLS and spatial hedonic, for a priori segmentations involving the spatial, structural and nested sub-markets.  It also draws general conclusions about the importance of detailed accessibility measures and spatial statistics in sub-market modelling. This study finds that the nested sub-market modelling using a spatial hedonic approach is most effective, followed by the spatial and structural sub-markets.  The OLS sub-market modelling generally reduces spatial autocorrelation but does not eliminate it.  There is a greater incidence of spatial autocorrelation when the market size, with measured by geographical area or density of dwellings is larger.  The spatial hedonic modelling improves the performance of the individual OLS models and the three segmentation approaches, although the relative performance of the latter remains unchanged.  Nevertheless, will the spatial hedonic, the entire market model outperforms the OLS model of structural sub-markets.  Flat-based OLS sub-market models benefit substantially from the spatial hedonic.  The results also suggest that an individual accessibility measure is more significant than the zonal measure because it is able to capture the micro effect of location on price.  Further, spatial statistics produce more accurate, robust and reliable estimates of implicit prices.

Recent studies of the valuation of real estate have concentrated on the use of hedonic pricing techniques in which the implicit prices of the component characteristics of an asset are inferred from the observed sale price using regression analysis. All of these studies include as explanatory variables one or more locational factors, such as distance to the central business district, as proxies for the effect that location has on the utility of land. In this research, the explicit consideration of the location of real estate in terms of the geographic or Cartesian coordinates (spatial attributes) of observed sales is shown to be a potential substitute for such proxies, either wholly or in part. Such use of spatial attributes could improve the usefulness of the hedonic methodology while at the same time significantly reducing cost and eliminating sources of error.

The empirical results from past research are quite clear. When the surrounding crime level goes up, housing prices go down. However, what has not been acknowledged in the previous literature is that different crimes might impact our willingness-to-pay heterogeneously. As most of the previous research is done through the usage of simple crime rates, this thesis acknowledges the relative severeness of different crimes. Using the newly developed crime harm index (CHI), the relative severity and harm inflicted by a specific crime is identified. The study is conducted in Sweden, Stockholm, using data for the year 2020. With the use of hedonic price equations, spatial models as well as graphical information system software, this thesis estimates a significant, and non-negligible negative relationship between increased area mean CHI and apartment prices. To the best of the author's knowledge, this is one of the very first analyses within the literature, which acknowledges the relative severeness of crimes, and the first to show a significant negative relationship between increased criminal harm and apartment prices. Further, the resulting estimates and method used in this thesis can be utilized to differentiate between the costs of different crimes, hence enabling precise cost estimates. These estimates could for example be of great use to policymaking, urban planners, and decision-making regarding safety investment.

The concepts of “energy sustainability” and “environmentally friendly” arouse extensive attention and the discussion on how to utilize, save and regulate energy and reduce pollution has become a dominant issue. The building sector in Europe is responsible for 40% of total energy consumption and 38% of total CO2 emissions, leading to economic, geopolitical and environmental concerns. An increasing number of studies have recognized the significant role that energy efficiency played in the residential market and the energy policies and the inner implication that promote or hinder the EPC program has aroused researchers’ concerns. This dissertation aims to explore the spatial implications of energy efficiency on housing price in Barcelona Metropolitan Area and furtherly detect the energy premium submarket in details as well as their policy implications. To well-fulfil this general objective, there are four specific objectives proposed: 1) To explore the possibility of selection biases when detecting the “green premium” in Barcelona residential market; 2) To explore the EPC impacts on housing price in different residential segmentations are uneven or not; 3) To explore the presence of spatial dependence (i.e. autocorrelation) when analyzing the impact of EPC on housing price; 4) To explore the presence of spatial heterogeneity when analyzing the impact of EPC on housing price. This dissertation has employed a series of Hedonic Price Models (HPMs) and spatial econometric models as well as other approaches or methods to fulfil the specific objectives. It has drawn a series of conclusion concerning each empirical study. Firstly, sample selection bias indeed exists and will lower the energy efficiency’s impacts on housing price. In our case, the green premium will reach to an increase of 12% if an apartment improves its energy efficiency from rating G to rating A. From an ordinal EPC perspective, about 2% growth of housing price along with energy efficiency rating improvement gradually (i.e. step by step in the G to A Spanish EPC Scale). At the same time, we found that selection biases in Barcelona mainly happened surrounding the area with a higher housing price and more university-educated citizens. From a real estate segmentation perspective, there are several highlights of energy premium performance. Secondly, consumers are willing to pay more for those tangible characteristics (e.g. heating or air conditioning) rather than an intangible and composite indicator. Interestingly, the housing price in “new apartment” segmentation market does not sensitive at all to energy efficiency which supposed that the EPC implication has been captured by new buildings’ structural quality. However, those cheapest apartments with a worst structural quality can enjoy considerable “energy premium” (reaching to 33%) if they renovated certificates from rating G to rating A. It is inferred that the poor people may regard this EPC label as one of the quality indicators for an apartment. It highlights that the spread and transparency of energy efficiency may fail to the public with a lower income/lower social class. Thirdly, empirical study III and IV confirmed the existence of spatial dependence and heterogeneity which contributed to the non-stationary distribution of energy premium. In sum, there are many limitations to this dissertation but it has synthesized a comprehensive model to check the spatial implication of energy efficiency on housing prices. In the future how to improve this compositive model and apply it in other case study are our aims.
Los conceptos de “sostenibilidad energética” y “ambientalmente amigable” han ganado relevancia, y la discusión sobre cómo utilizar, ahorrar y regular la energía para reducir la contaminación, se ha convertido en un tema dominante. El sector de la construcción en Europa es responsable del 40% del consumo total de energía y del 38% de las emisiones totales de CO2, lo que genera preocupaciones económicas, geopolíticas y medioambientales. Por esta razón, varios países y distritos de Europa han comenzado a establecer sistemas de gestión energética de edificios para controlar, supervisar y mejorar la eficiencia energética de las edificaciones. Entre ellos se incluyen los Certificados de Eficiencia Energética (EPC), lanzados en 2003, el Método de Evaluación Ambiental del Building Research Establishment (BREEAM), que se lanzó en el Reino Unido en 1990, la certificación de Alta Calidad Ambiental (HQE) en Francia y Minergie en Suiza. Asimismo, una gran cantidad de estudios han reconocido la importancia de la eficiencia energética en el mercado residencial. Donde las implicaciones internas de las políticas energéticas que promueven o dificultan el programa de EPC, han despertado la preocupación de los investigadores. En este contexto, la presente tesis doctoral ha buscado contribuir en este campo de investigación, con especial atención a la Zona Climática Mediterránea que no ha sido bien discutida hasta el momento. En general, El presente trabajo tiene como objetivo explorar las implicaciones espaciales de la eficiencia energética en el precio de la vivienda en el Área Metropolitana de Barcelona y detectar con más detalle el submercado de la prima energética, así como sus implicaciones políticas. Para cumplir con este objetivo general, se proponen cuatro objetivos específicos: 1) evaluar los posibles sesgos de selección a la hora de detectar la “prima verde” en el mercado residencial de Barcelona; 2) analizar la desigualdad de los impactos del EPC en el precio de la vivienda en diferentes segmentaciones residenciales; 3) evaluar la dependencia espacial (es decir, autocorrelación) al analizar el impacto del EPC en el precio de la vivienda; 4) examinar la heterogeneidad espacial al analizar el impacto del EPC en el precio de la vivienda. Como la segunda zona urbana más grande con clima mediterráneo y con las viviendas más eficientes energéticamente de España, el Área Metropolitana de Barcelona es un buen ejemplo para analizar el comportamiento de la eficiencia energética de esta región. En nuestro caso, el precio de venta de los apartamentos y otras variables relativas que impactan en los precios de la vivienda se recopilaron en 2014 y 2016 respectivamente. Para esta investigación se han empleado una serie de Modelos de Precios Hedónicos (HPM) y modelos econométricos espaciales, así como otros enfoques o métodos para cumplir con los objetivos específicos. En estudio empírico I, se aplica el modelo de dos pasos de Heckman para determinar si existen sesgos en la selección de la muestra. Una vez que haya un sesgo de selección, se introducirá una variable de instrumento - "relación inversa de Mills" en el HPM para corregir dichos sesgos. Finalmente, se presenta una breve comparación entre los resultados de la estimación de OLS y HPM sin sesgo para ver cómo los sesgos de la muestra de selección influyen en los resultados, positiva o negativamente. Después de corregir los sesgos mediante la selección de la muestra, el estudio empírico II empleó un HPM tradicional con una variable de sistema integral en cuanto a calidad estructural, accesibilidad, vecindario y medio ambiente, así como el aspecto socioeconómico. Luego, se utiliza un análisis de conglomerados de dos pasos para identificar la existencia de segmentación inmobiliaria. De acuerdo con el desempeño de varias características de la segmentación, se especifican varios HPM para explorar cómo la eficiencia energética impacta en el precio de la vivienda a nivel local. Los estudios empíricos III y IV, introducen el Modelo de Error Espacial (SEM) y el Modelo de Regresión Ponderada Geográficamente (GWR) para resolver las implicaciones espaciales, donde el primero es para el problema de la dependencia espacial y el segundo para la heterogeneidad espacial. Cada uno de los estudios empíricos ha arrojado conclusiones particulares. En primer lugar, existe un sesgo de selección de la muestra que reducirá los impactos de la eficiencia energética en el precio de la vivienda. En nuestro caso, la prima verde alcanzará un aumento del 12% si un apartamento mejora su eficiencia energética de la calificación G a la calificación A. Desde una perspectiva EPC ordinal, alrededor del 2% de crecimiento del precio de la vivienda junto con la mejora de la calificación de eficiencia energética gradualmente (es decir, paso a paso en la escala EPC española de G a A). Al mismo tiempo, encontramos que los sesgos de selección en Barcelona ocurrieron principalmente en las zonas de mayor precio de vivienda y el mayor número de ciudadanos con educación universitaria. Desde una perspectiva de segmentación inmobiliaria, hay varios aspectos destacados del desempeño de la prima energética. En segundo lugar, los consumidores están dispuestos a pagar más por aspectos tangibles (por ejemplo, calefacción o aire acondicionado) que intangibles y compuestos. Curiosamente, el precio de la vivienda en el mercado de segmentación de "apartamentos nuevos" no es sensible en absoluto a la eficiencia energética, lo que supuso que la implicación del EPC se había reflejado en la calidad estructural de los nuevos edificios. Sin embargo, aquellos apartamentos más baratos y de menor calidad estructural son acreedores de una considerable “prima energética” (llegando al 33%) si renovaron los certificados de la calificación G a la calificación A. Se infiere que las personas de menos ingresos pueden considerar la etiqueta del EPC como un indicador de calidad para un apartamento, aunque se destaca que la difusión y transparencia de la certificación de la eficiencia energética puede presentar más fallas al público de las clases sociales más bajas. En tercer lugar, los estudios empíricos III y IV confirmaron la existencia de dependencia espacial y heterogeneidad que contribuyó a la distribución no estacionaria de la prima energética. En resumen, aunque existe una gran cantidad de limitaciones en el estudio de este tema, el presente trabajo ha logrado sintetizar un modelo integral para verificar la implicación espacial de la eficiencia energética en los precios de la vivienda. Por lo que, en futuras investigaciones buscará mejorar este modelo y replicarlo en otros casos de estudio.

This chapter compares forecasts of the median neighborhood prices of residential single-family homes in Cambridge, Massachusetts, using parametric and nonparametric techniques. Prices are measured over time (annually) and over space (by neighborhood). Modeling variables characterized by space and time dynamics is challenging. Multi-dimensional complexities—due to specification, aggregation, and measurement errors—thwart use of parametric modeling, and nonparametric computational techniques (specifically genetic programming and neural networks) may have the advantage. To demonstrate their efficacy, forecasts of the median prices are first obtained using a standard statistical method: weighted least squares. Genetic programming and neural networks are then used to produce two other forecasts. Variables used in modeling neighborhood median home prices include economic variables such as neighborhood median income and mortgage rate, as well as spatial variables that quantify location. Two years’ out-of-sample forecasts comparisons of median prices suggest that genetic programming may have the edge.

Studies considering street environment quality’s impact on housing value were limited to top-down variables such as the green ratio measured from satellite maps. In contrast, this study quantified street views’ impacts on the value of second-hand commodity residential properties in Shanghai based on analysis of street view imagery. (1) It applied computer vision to objectively measure street features from largely accessible street view imagery. (2) Based on the classical urban design measures frameworks, it applied machine learning to evaluate human perceived street quality as street scores systematically, in contrast to the common practice of doing so in a more intuition-based fashion. (3) It further identified important indicators from both human-centered street scores as well as the more objective street feature measures with positive or adverse effects on property values based on a hedonic modeling method. The estimation suggested both street scores and features are significant and non-negligible. For the perceived street scores (from 0-10 scale), neighborhoods with a unit increase in their “enclosure” or “safety” score enjoy price premium of 0.3% to 0.6%. Meanwhile, streets with 10% greater tree canopy exposure are attributable to a 0.2% increase in the property value. This study enriched our current understanding at a micro level of the factors that impact property values from the perspective of the built environment. It introduced human-centered perception of street scores and objective measures of street features as spatial variables into the analysis of neighborhood attribute vectors.

Owner-occupied housing is both a place to live and also the most important asset in many households’ portfolio. Accurately predicting of house prices is therefore of great interest to the general public. This paper aims to compare the housing price prediction accuracies of Hedonic Model (HM) and Artificial Neural Networks (ANNs). In order to achieve this aim, two techniques’ prediction results were compared by using four performance criteria: RMSE, MAE, MAD, and Theil’s U statistic. This study uses the HM and ANNs to empirically determine the house prices in Turkey. HM is the standard technique for modeling the behavior of house prices over the past three decades and is based on micro economic theory. The non-linear relationship between house price and its determinants can be modeled by an ANN, so it is employed in this paper as an alternative method. Empirical results revealed that ANNs performed better than HM in house price predictions, indicating that ANNs could be useful for prediction of house prices. More clearly, the performance criteria from the ANNs are smaller than those from the HM by roughly 60-90%. For instance, the ANN model has about 77 percent lower RMSE, 91 percent lower MAE, 64 percent lower MAD, and 77 percent lower Theil’s U statistic than those of the HM.

Abstract The offshore wind farm industry has identified further refinement of marine operations as necessary to realize the lower strike prices seen in recent subsidy auctions. This requires extending working times by taking advantage of weather windows, even when operating in more remote sites. Key to this will be increasing the accuracy of forecasts and live metocean data from site for effective and safe operation scheduling. In recent years, statistical models or deep learning-based models, by learning spatial and temporal patterns in observations have shown their potential to support or even partly replace numerical weather modelling to provide accurate forecasts. The present paper implements a machine learning approach utilizing a nonconvex low-rank tensor completion considering truncated nuclear norm algorithm (LRTC-TNN) which can characterize the spatial and temporal dependencies rooted in the data to fill gaps in measurement data from wave buoys. The performance is assessed by manually masking valid data thereby introducing three types of missing entries. The proposed method is shown to successfully fill datasets missing up to 20% of the data with R2 values exceeding 0.9. The results are also compared against other intuitive methods including linear interpolation, cubic spline interpolation, and mean historical. Compared to these, the present method is shown to have more reasonable trends. Finally, sensitivity considering the ratio of missing data, the type of missing data, and two hyper-parameters of the algorithm were compared to characterize their impacts on the results and advise potential improvements. This work demonstrates multivariate time series gap-filling with arbitrary missing ratio and sensor availability that can be extended and deployed to sensor networks for possible forecasting applications.