Search Results (67)

The accurate estimation of urban property values is a key challenge for appraisers, market participants, financial institutions, and urban planners. In recent years, machine learning (ML) techniques have emerged as promising tools for price forecasting due to their ability to model complex relationships among variables. However, their application raises two main critical issues: (i) the risk of overfitting, especially with small datasets or with noisy data; (ii) the interpretive issues associated with the “black box” nature of many models. Within this framework, this paper proposes a methodological approach that addresses both these issues, comparing the predictive performance of three ML algorithms—k-Nearest Neighbors (kNN), Random Forest (RF), and the Artificial Neural Network (ANN)—applied to the housing market in the city of Salerno, Italy. For each model, overfitting is preliminarily assessed to ensure predictive robustness. Subsequently, the results are interpreted using explainability techniques, such as SHapley Additive exPlanations (SHAPs) and Permutation Feature Importance (PFI). This analysis reveals that the Random Forest offers the best balance between predictive accuracy and transparency, with features such as area and proximity to the train station identified as the main drivers of property prices. kNN and the ANN are viable alternatives that are particularly robust in terms of generalization. The results demonstrate how the defined methodological framework successfully balances predictive effectiveness and interpretability, supporting the informed and transparent use of ML in real estate valuation. Full article

A significant share of many commercial banks’ portfolios consists of residential mortgage loans provided to individuals and families. This paper examines the default and rational prepayment risk of single-borrower (residential) mortgage loans based on an option pricing model that captures the skewness and kurtosis of the house prices returns’ distribution via the shifted lognormal distribution. Equilibrium option-adjusted credit spreads are obtained from the implementation of the model under plausible values of the relevant parameters. The methodology involves numerical experiments, using a shifted binomial tree model by Haathela and Camara and Chung, to evaluate the effects of the loan-to-value (LTV) ratio, asset volatility, interest rates, and recovery costs on mortgage valuation. Findings indicate prepayment risk significantly influences loan value, as it limits upside potential, while LTV and volatility directly impact default risk. The shifting parameter (θ) in the asset distribution proves essential for accurate risk assessment. Conclusions emphasize the need for mortgage underwriting to consider specific asset characteristics, optimal loan structures, and prevailing risk-free rates to avoid underestimating risk. This model can aid in the more robust pricing and management of mortgage portfolios, especially relevant in regions with substantial mortgage-backed exposure, such as the European banking system. Full article

Europe faces a situation where housing represents the main savings for most of the population, while the majority of homeowners are seniors aged over 65. The desire to supplement pensions has led to a growing interest in generating income from these savings, with bare ownership emerging as a notable option. This solution makes it possible to transfer the ownership of the home while maintaining usufruct rights for the duration of the owner’s lifetime. This paper examines the status of bare ownership in the city of Rome by web scraping the house offers published on web portals and segmenting those offered as bare ownership. Machine learning analysis based on neural networks and binary logit regression allows for the observation of the particular behavior of the housing supply in bare ownership; it shows the different intrinsic and extrinsic characteristics that determine this Real Estate segment. The findings highlight the development of a growing market strongly influenced by the location of assets. These findings provide valuable insights for both investors and urban planners regarding changes in urban dynamics processes. Full article

The proliferation of abandoned houses in rural South Korea poses significant challenges to sustainable rural development, driven by declining birth rates, aging populations, and urban migration. However, effective policy implementation is hindered by the lack of understanding of the negative externalities caused by abandoned houses. This study fills this gap by estimating the negative externalities associated with abandoned rural houses using discrete choice experiments. Surveys targeting individuals planning rural relocations and potential tourists considering rural stays were conducted to quantify the external costs. Our findings reveal that the marginal willingness to pay associated with abandoned houses is negative and decreases with an increasing number of abandoned houses nearby, both in the context of house purchases and rural stays. Extrapolating these results to the national level, we estimate the aggregate negative externalities value to be approximately 4.2 trillion KRW per year, highlighting significant negative externalities in rural areas nationwide. The implications of our analysis underscore the severity of negative externalities from abandoned houses, which may surpass the value of housing services, discourage migration, and prompt residents to leave rural communities, thus exacerbating the issue. Our study emphasizes the necessity for further research and policy interventions to address the negative externalities associated with abandoned rural houses, offering insights into the potential use of discrete choice experiments in similar contexts. Full article

The possibility of carrying out the cultivation of numerous plant species in vertical farming highlights the need for policy makers to determine the cadastral value of the buildings in which these production activities are carried out. In this regard, estimates of buildings intended to host vertical farming are illustrated according to the procedure established by Italian cadastral legislation, which establishes that the fiscal value of buildings intended for vertical farming must be estimated through their market value. Appraisals is carried out using the direct capitalization method but follow two different approaches. One approach is based on the expertise of the appraiser, who acts by making assessments through subjective and arbitrary choices. The other approach is based on the use of best practices, as indicated by international evaluation standards that follow appropriate methodologies. Our comparison between the two approaches focuses on determining the capitalization rate, which determines the estimated value. The market value estimated using the procedures recognized by the valuation standards appears to be more valid methodologically and more reliable. This is demonstrated by applying yield capitalization to the same income cash flow in both formulations. Additionally, through the identification of the conversion cash flow, useful details on financial flow can be obtained and used to determine the value. The obtained results may be useful for public operators for the purposes of determining the value of assets for tax purposes. More generally, they are also useful from a methodological and application point of view in real estate valuation and support the development of tools for making efficient investment choices. Full article

The housing market in Dar es Salaam, Tanzania, is expanding and with it a need for increased market transparency to guide investors and other stakeholders. The objective of this paper is to evaluate machine learning (ML) methods to appraise real estate in formal and informal housing markets in this nascent market sector. Various advanced ML models are applied with the aim of improving property value estimates in a market with limited access to information. The dataset used included detailed property characteristics and transaction data from both market types. Regression, decision trees, neural networks, and ensemble methods were employed to refine property appraisals across these settings. The findings indicate significant differences between formal and informal market valuations, demonstrating ML’s effectiveness in handling limited data and complex market dynamics. These results emphasise the potential of ML techniques in emerging markets where traditional valuation methods often fail due to the scarcity of transaction data. Full article

This study explores the recent emergence of traditional Korean houses and hanoks as markers of cultural capital in Seoul, South Korea. While the ownership of detached houses itself can be a symbol of wealth in Seoul, traditional-style houses have become increasingly associated with luxurious living, particularly after the successful remodeling of hanoks in metropolitan settings such as Bukchon in Seoul. This study employs the critical luxury studies method to analyze the recent rise in hanok construction/remodeling among elites, and illustrates how traditional architectural forms have become status markers. Although the regeneration of traditional houses in cities has been examined from the perspective of gentrification or touristic cultural consumption, less academic attention has been placed on the phenomenon from the perspective of the homeowners’ taste. This study examines how traditional architecture has become a form of acceptable luxury through a media analysis of published articles and interviews with the residents of hanoks. This study argues that protecting endangered traditions and rich sensory experiences function as important moralizing factors in luxury housing, indicating that sociocultural valuation becomes as significant as market valuation. Full article

In post-war environments, property valuation encounters obstacles stemming from widespread destruction, population displacement, and complex legal frameworks. This study addresses post-war property valuation by integrating war-related considerations into the ISO 19152 Land Administration Domain Model, resulting in a valuation information model for Syria’s post-war landscape, serving as a reference for property valuation in conflict-affected areas. Additionally, property valuation is enhanced through visualization modeling, aiding the comprehension of war-related attributes amidst and following conflict. We utilize data from a field survey of 243 Condominium Units in the Harasta district, Rural Damascus Governorate. These data were collected through quantitative interviews with real estate companies and residents to uncover facts about property prices and war-related conditions. Our quantitative data are analyzed using inferential statistics of mean housing prices to assess the impact of war-related variables on property values during both wartime and post-war periods. The analysis reveals significant fluctuations in prices during wartime, with severely damaged properties experiencing notable declines (about −75%), followed by moderately damaged properties (about −60%). In the post-war phase, rehabilitated properties demonstrate price improvements (1.8% to 22.5%), while others continue to depreciate (−55% to −65%). These insights inform post-war property valuation standards, facilitating sustainable investment during the post-war recovery phase. Full article

Rapid urban growth necessitates focused attention regarding its policy and governance to ensure affordable housing, transparent and efficient real-world systems, reduce social inequalities, and promote sustainable development. This study delves into the semantics and ontology for developing a Land Administration Domain Model (LADM) profile in the context of Pakistan’s Land Administration Systems (LASs), which currently face issues due to manual record-keeping, lack of transparency, frauds, and disintegration. Establishing a baseline through Record of Rights (RoR) and Property Information Report (PIR), alongside surveying and mapping procedures defined by laws and rules, forms the foundation for LADM profile development. This study explores the transition from manual LAS to 2D/3D representation, using LADM as a conceptual guideline. The LADM profile’s three key packages—PK_Party, PK_Administrative, and PK_SpatialUnit—a sub-package, and external classes are examined, with proposals for digitalisation and modernisation. Additionally, the study includes expert consultation, and highlights the significant support that the LADM implementation offers to achieve Sustainable Development Goals (SDGs) in Pakistan. In conclusion, the study underscores the need for a comprehensive and inclusive approach to address organisational overlaps and ambiguities within LAS, positioning PK LADM as a transformative force for sustainable urban LAS in Pakistan, aligning with broader SDGs. Recommendations include exploring realistic land valuation, integrated ownership and location verification systems, addressing historical survey data challenges, and promoting wider stakeholder adoption for sustainable 2D/3D urban LAS using LADM and its edition II as a way forward towards the creation of a smart city and digital twin. Full article

The preservation of cultural heritage plays a key role in the development of society. To preserve cultural heritage, protection zones are established, which represent an encumbrance on land plots and, therefore, should be taken into account in the valuation process. Currently, there is a problem that mass (cadastral) and individual valuation methods do not necessarily include cultural heritage objects and their zones in cost coefficients. The absence of a mechanism to address their individual characteristics in the real estate valuation system has a significant impact on the value of real estate and leads to unjustifiably inflated market value and, as a consequence, to disputing the results of cadastral valuation. This article is devoted to determining the impact of protection zones of cultural heritage objects on the value of land intended for individual housing construction, using the example of the city of Orenburg. This article considers various methods of identifying patterns of the influence of zones with special conditions of use of the territory on the market value of land and substantiates the use of the method of comparative sales in the conditions of a low-active land market in Orenburg, a statistical analysis of market information, on the basis of which the type of activity of the real estate market in Orenburg was determined. The patterns of the calculation of corrections for the remoteness of the studied land plots from the objects of the transport and social infrastructure of Orenburg were revealed in this work as well. Through the method of paired sales within the framework of an individual assessment of the land plot intended for individual housing construction, the diminishing impact of the zones of protection of cultural heritage objects on the market value of land plots was revealed. This allows for conclusions to be drawn as to whether objects of cultural heritage have an impact on the value of real estate, and as a result, there is a need to modify the applied methods of mass and individual real estate valuation within the boundaries of historical settlements. Full article

Brownfield redevelopment projects are often perceived as more risky than greenfield investment, and financing opportunities may be more limited and expensive. Different financial support projects have been developed to support regeneration projects, and empirical evidence has shown that all buildings near the intervention area may benefit from an increase in prices once the brownfield project is complete. The article considers the Connecticut market and evaluates the characteristics of the brownfield projects that had access to a financial support program (loan or grant), the impact of the regeneration process on the liquidity of the housing market, and the gap between the price and the appraisal value of the residential unit. Target areas for this type of financing program are mainly characterized by low income, a high density of population, a high incidence of homeowners, and a high crime rate. Once completed, the brownfield requalification has an impact on the housing market because the brownfield recovery reduces the number of house sales due to the increase in the average price in the surrounding area and makes the selling price more consistent with the appraisal valuation. The empirical evidence provided may be useful for public institutions that are suffering from budget constraints and have to prioritize areas for financial support solutions. Full article

In Türkiye, many changes have been made in the law within the past fifty years to determine the real estate tax value close to the real market value. However, the changes did not establish a fair valuation system for determining real estate tax. Despite the regulations and records of immovable properties with a geographic information system (GIS)-based inventory in recent years, the problem of leakage loss in real estate tax was still not resolved. Within the scope of this study, a mass appraisal model was created with a dataset of 499 independent sections including trading values from the last year in the district of Kayseri to determine the real estate tax leakage loss rates. Multiple regression analysis (MRA) and artificial neural network (ANN) methods, widely used in mass appraisal, were used in the analysis. Considering the analysis of the test data and the model performances, the ANN model was found to give better results than the MRA model. To conclude this study, the housing values obtained with the mass appraisal methods and the real estate tax values obtained with the existing system were compared, and a 3.7-fold difference was found between them. Full article

The harmful impacts of the ongoing Sargassum invasions in the Atlantic Ocean include fish kills, skin and eye irritation, beach fouling, and declines in fisheries and tourism in West Africa and the Americas. This study was conducted to address important gaps in the non-market valuation literature and support the design of effective adaptation policies to reduce the harmful impacts of algal blooms. Contingent valuation survey data and linear mixed-effects regression models were utilized to estimate the drivers of willingness to pay (WTP) and willingness to contribute time (WTCT) for the management of invasive Sargassum seaweeds in Ghana. The study revealed that income, education, family size, years of residence, sex, attitudes, and political affiliation are significant drivers of WTP, while distance to the beach, occupation, house ownership, attitudes, and political affiliation are also significant predictors of WTCT. Hence, only attitudes about invasive seaweeds and political affiliation influence both WTP and WTCT. The findings suggest that for developing countries to generate enough funding and adequate economic support for coastal resource conservation, they should design local resource protection programs that give residents the option to contribute both time and money. Full article

Increased time spent in nature can enhance physical health and mental wellbeing. The UK Government’s ‘25 Year Environment Plan’ recommends extending the health benefits of contact with nature to a wider group of people, including those with mental health challenges. This study investigated whether nature-based interventions (NBIs) for people with mild mental health challenges could generate a positive social return on investment (SROI). Between May 2017 and January 2019, 120 participants at six outdoor sites in Wales participated in a 6 to 12-week NBI, which consisted of a weekly 2- to 4-h session. Quantitative data were collected from baseline and follow-up questionnaires identifying participant demographics and measuring mental wellbeing, physical activity, self-efficacy, and social trust. Wellbeing valuation generated a range of social value ratios by applying the Housing Association Charitable Trust (HACT) Social Value Calculator (SVC 4.0) and HACT Mental Health Social Value Calculator (MHSVC 1.0). Seventy-four participants (62%) completed follow-up questionnaires at 6 months. SROI ratios were calculated using the SVC for physical activity, self-efficacy, and social trust. The MHSVC generated social value ratios for mental wellbeing. The base case results revealed a positive social value ratio for participants, ranging from British Pound Sterling (GBP) 2.57 to GBP 4.67 for every GBP 1 invested, indicating favourable outcomes in terms of value generated. Full article

Residential property values are influenced by a combination of physical, socio-economic and neighbourhood factors. This study investigated the influence of public schools on residential property prices. Relatively few existing models have taken the spatial heterogeneity of different submarkets into account. To fill this gap, three types of valuation models were applied to sales data from both non-strata and strata properties, and how the proximity and quality of public schools have influenced the prices of different residential property types was examined. The findings demonstrate that an increase of one unit in the normalised NAPLAN score of primary and high schools will lead to a 3.9% and 1.4%, 2.7% and 2.8% rise in housing prices for non-strata and strata properties, respectively. It is also indicated that the application of geographically weighted regression (GWR) can better capture the varying effects of schools across space. Moreover, properties located in the catchment of high-scoring schools in northern Greater Sydney are consistently the most influenced by school quality, regardless of the property type. These findings contribute to a comprehensive understanding of the relationships between public schools and the various submarkets of Greater Sydney. This is valuable for the decision-making processes of home buyers, developers and policymakers. Full article