Real Estate

Property condition assessment is a critical step in residential real estate investment underwriting, motivating after-repair value (ARV) estimates and rehabilitation cost projections. Traditional approaches rely on in-person inspections or manual photo review by experienced investors—processes that are time-consuming, subjective, and do not scale. Prior computer vision work on building analysis has focused on structural defect detection using convolutional neural networks but has not addressed the holistic, room-level condition assessment needed for residential investment decision-making. This paper presents a per-room analysis framework that leverages multimodal large language models (MLLMs) to assess the condition of residential properties from photographs. The framework analyzes each photo independently at the room level—detecting the room type, condition category, condition score, material features, and visible issues. Condition output is intended to feed a separate downstream rehabilitation cost and ARV estimation model that is outside the scope of this paper; the present empirical evaluation is restricted to per-photo condition assessment and inter-rater agreement with human experts. I evaluate the framework on two complementary datasets: (i) a primary per-image condition evaluation on 57 photographs from 14 real off-market properties in the Memphis, TN MSA, spanning three condition tiers (Fixer, Outdated, Standard), with independent labels from two experienced real estate investors; (ii) a secondary room classification evaluation on the public REI Dataset (51 attempted, 39 successful, 12 HTTP-503 failures). The room classification accuracy was 76.5% intention-to-analyze on REI (100% per-protocol on the 39 successful calls; 23.5% API failure rate) and 82.5% on the concierge dataset. The inter-rater agreement on the concierge dataset, with 95% bootstrap CIs (5000 resamples) and Spearman’s $\rho$ as primary score statistic, was as follows: Cohen’s $\kappa =0.773$ ($95\%$ CI $[0.64,0.90]$) between Labeler A and the MLLM (weighted $\kappa =0.853$ $[0.76,0.94]$; $\rho =0.906$); and $\kappa =0.502$ $[0.35,0.66]$ between Labeler B and the MLLM ($\rho =0.858$); both bracket the human–human reliability of $\kappa =0.590$ $[0.42,0.74]$ ($\rho =0.807$). The MLLM’s $\kappa$ asymmetry across the two labelers is statistically significant ($\Delta \kappa =0.271$, $95\%$ bootstrap CI $[0.115,0.429]$, $p=0.0004$), which I attribute to plausible training distribution and labeling style differences. A blind re-labeling sensitivity analysis on a stratified 15-image subsample yields anchoring-corrected $\kappa$ estimates of approximately $0.65$ (Labeler A) and $0.35$ (Labeler B); the headline anchored values therefore sit at the upper bound of plausible blind-equivalent agreement. Failure modes concentrate at the Outdated tier and at the Outdated–Standard boundary, where humans themselves disagree most, indicating intrinsic taxonomy ambiguity rather than a model artifact. I make no claim to multi-market generalization and present multi-market extension as ongoing work. Full article

Purpose: This paper aims to systematically synthesize academic research published between 2020 and 2025 that investigates environmental, social, and governance (ESG) ratings and scores, with a focus on their methodologies, comparative performance, and impact on firm outcomes. Design/methodology/approach: A systematic literature review (SLR) was conducted using the Lens.org scholarly database. A structured title search retrieved 334 open access journal articles published between 2020 and May 2025 containing the terms “ESG Score”, “ESG Rating”, or “ESG Rater”. The PRISMA 2020 protocol guided the selection and screening process. Findings: The literature exhibits growing concern about the divergence among ESG ratings, the methodological opacity of rating providers, and the variable financial implications of ESG scores. Common themes include score disagreements, rating agency biases, and emerging models for standardizing ESG assessments. Originality: This review provides the most up-to-date synthesis of the ESG rating literature, focusing exclusively on articles explicitly addressing ESG ratings or scores in their titles. It contributes clarity to the fragmented ESG measurement space by organizing findings around key methodological and evaluative debates. Full article

This study develops and evaluates a two-stage machine learning framework for forecasting the condominium price index of pre-pandemic market data of Frankfurt am Main, Germany, one quarter ahead. To the best of the author’s knowledge, it is the first study to combine German micro-level transaction and listing data, socioeconomic variables and macro-financial indicators in a single residential price-forecasting framework. Furthermore, it provides the first evidence on machine learning-based transaction price index forecasting in Germany. Methodologically, the framework links disaggregated and aggregate forecasting. In stage 1, prices per square metre are estimated for four market segments using ordinary least squares, random forest, extreme gradient boosting, and a stacked ensemble in a strictly out-of-sample expanding-window design. In stage 2, these predictions are combined with lagged index values and macro-financial indicators to forecast the city-wide index. The stage 2 model achieves a relative root mean squared error of 2.25% and a mean absolute percentage error of 1.85%, outperforming a naïve persistence benchmark by reducing root mean squared error by 23%. Model interpretation indicates that price persistence dominates stage 1, reflecting market inertia, while lagged macro-financial variables and location quality composition drive index forecasts, pointing to delayed financial market transmission and heterogeneous submarket dynamics. Full article

The real estate sector has increasingly shifted toward digital platforms, where content sentiment plays a crucial yet understudied role in driving user engagement. While sentiment analysis has been widely applied in retail and finance, its impact on real estate web traffic remains poorly understood, particularly in competitive digital marketplaces. This study examines the relationship between sentiment in web content and the traffic it attracts on residential real estate websites in South Africa. Specifically, it examines how different sentiments associated with the type of content (articles versus property listings) influence total monthly web traffic and user engagement. A quantitative analysis of six years (2017–2023) of scraped data from Property24, Remax, and Private Property employed R (rvest, sentimentr, and stats packages) for web scraping, sentiment analysis, and ANOVA testing to evaluate relationships between content sentiment, type (listings vs. articles), and web traffic metrics. The analysis revealed a significant impact of sentiment on web traffic, indicating that the sentiment of web content influences visitor numbers. Specifically, property listings generated a total of 16,780,623 monthly visitors, significantly surpassing the 13,407,521 visitors attracted by articles. This study contributes empirical evidence regarding the influence of content sentiment and content type on web traffic within the South African real estate market. It highlights the critical role of sentiment in shaping web traffic and potentially user engagement and provides actionable insights for real estate developers and marketers seeking to optimize their content strategies to improve user attraction and retention. Full article

The real estate sector continues to face challenges such as inefficiencies, fraud risks, and high transaction costs stemming from opaque processes and heavy reliance on intermediaries. These challenges highlight the need for transparent and efficient solutions to support secure real estate transactions and management. While a growing body of literature has examined blockchain applications in real estate, existing studies are often fragmented and predominantly descriptive, with limited systematic synthesis of evidence and insufficient attention to governance and institutional contexts. This study aims to systematically examine and synthesise the benefits and challenges of blockchain technology in real estate, providing evidence-based insights for practitioners and policymakers. Using a Systematic Literature Review (SLR) approach, peer-reviewed publications from 2016 to 2025 were analysed to identify blockchain applications, reported outcomes, and implementation barriers. The findings reveal that blockchain has been applied in land registration (e.g., Sweden, India, Serbia), valuation systems, decentralised housing finance, and tokenised investment platforms (e.g., Exporo, RealT). The reported benefits include reduced fraud, enhanced transaction efficiency, transparency, and expanded investment access through fractional ownership. However, regulatory uncertainty, scalability limitations, data privacy risks, and low stakeholder awareness remain key barriers. Ethical issues such as digital exclusion and data exposure also require further consideration. Compared with the more advanced adoption observed in Europe and North America, supported by established regulatory frameworks and digital land governance initiatives, this review identifies relatively slower uptake in parts of the Asia-Pacific region, particularly in Australia and Malaysia. It highlights a critical need for future research on legal recognition, privacy-enhancing technologies, and governance frameworks, particularly regarding blockchain applications in property development and urban planning processes. By integrating technological and governance perspectives, this study provides a more comprehensive and structured understanding of blockchain adoption in real estate systems. Full article

This research examines how the relationship between cities and rural areas has evolved in light of the profound transformation affecting rural areas of high landscape value, which has been driven by the expansion opportunities granted to the real estate sector by urban planning regulations. The role of the landscape dimension in interpreting the relationship between territorial wealth and landscape value is considered, based on the convergence of two complementary disciplinary perspectives on territory: land planning and valuation science. Against this backdrop, and with a view to containing the progressive contamination of rural and agricultural heritage by the real estate sector, this study proposes a structured observation, valuation, interpretation, and regulatory tool to support the development of territorial planning in areas significantly characterized in terms of rural landscape value. The proposed tool is based on evidence regarding the phenomenon of building expansion in the agricultural territory of a municipality in southeastern Sicily, where favorable conditions for the development of the building sector exist, such as the vastness of the municipal territory and extensive farming as the mainstay of agricultural activity. This wider sub-regional area has also received attention due to the over-tourism phenomenon that has occurred in its cities of art. The evaluation approach experienced is a value-based representation of the evolution of this process over three observation periods: 2000, 2007, and 2012, relating the quantitative observation of the building expansion to the connected qualitative impact on rural landscape. It is the result of coordinating a large set of data in a hierarchical model of indices that converge to construct a synthetic index of rural landscape resilience. This achievement is based on the linguistic progression of “lexicon”, “semantics”, “syntax”, and “pragmatics”, each of which robustly supports “observation”, “valuation”, “interpretation”, and “planning”, respectively. The final stage is based on the convergence of explanatory indices, which are developed by coordinating evidence and assessments (factual and value judgements). This stage enables the proposal of a constraints system that supports a modus vivendi between the interests of the real estate sector and the values of the rural landscape in such a rich and fragile area. Full article

Housing markets display geographical linkages that contravene conventional regression assumptions; yet, Central and Eastern European towns are markedly underrepresented in spatial econometric research. This study provides a systematic spatial econometric analysis of Zagreb’s housing market. It looks at both asking sale and rental prices throughout the city’s 17 administrative districts. There are five model specifications used in the analysis: Ordinary Least Squares (OLS), Spatial Lag of X (SLX), Spatial Autoregressive Model (SAR), Spatial Error Model (SEM), and Spatial Durbin Model (SDM). The findings demonstrate significant positive spatial autocorrelation in both markets: Global Moran’s I = 0.29 (p = 0.007) for sales and 0.42 (p < 0.001) for rents. LISA analysis finds important groups of high-priced homes in the center districts and lower-priced homes on the edges. Spatial models significantly surpass OLS: SLX exhibits AIC enhancements of 9.90 (sales) and 20.20 (rentals), but SAR and SEM yield no enhancements, suggesting that local spillover effects from adjacent characteristics prevail over global spatial diffusion or correlated shocks. The higher Moran’s I and AIC gains in rental markets show that there are different spatial processes for different types of tenure. These results address a significant empirical deficiency in post-socialist housing research, illustrate that neglecting spatial dependencies may lead to biased estimates and reduced model performance, and furnish methodologically sound evidence that spatial econometric techniques are essential for accurate modeling for precise urban housing analysis in intermediate-sample scenarios. Policy implications stress the need to use spatial approaches in choices about property value, forecasting, and urban planning. Full article

The correct valuation of collateral supporting real estate loans has always been a key issue for the stability of the credit system. Substandard lending practices and the absence of uniform valuation approaches have historically contributed to the accumulation of non-performing loans. In recent years, several regulatory measures operating at both the European and national level have introduced principles, rules and procedures aimed at standardizing the valuation of properties pledged as collateral for credit exposures. These interventions seek to promote greater transparency, consistency, and prudence in property appraisals, thereby enhancing the soundness and resilience of the financial system. In January 2025, the updated Regulation (EU) 575/2013 came into force, incorporating the Basel III reform (also referred to as Basel 3+ or Basel IV). Among the innovations introduced, the concept of property value (PV) is particularly relevant, a prudential value that excludes expectations of price growth and considers the sustainability of the value over time in relation to the duration of the loan. PV is defined as a derived value with respect to market value (MV), determined by considering the main current and forward-looking risk factors that may arise during the life of the loan, including environmental, social and governance (ESG) risks, the intrinsic characteristics of the property and expectations regarding the economic cycle. This paper proposes a quantitative model for the determination of PV, applied to a practical case involving a residential property located in a medium-sized city in Italy’s Veneto region. The model adopts a deterministic and a probabilistic approach, the latter implemented through Monte Carlo simulation, which is indeed a generalization of the deterministic one. The model links the assessment of PV to the possible evolution of the property’s key parameters and the real estate cycle over the duration of the loan. It was tested under the assumption of a twenty-year mortgage originated in 2025 for the purchase of a residential property in Italy, considering two alternative locations: a suburban area and a city-centre area. The analysis conducted showed a substantially higher MV haircut for the suburban property compared with the central location. This difference reflects the fact that PV is less sensitive to real estate cycle fluctuations in more premium, central locations. Furthermore, the use of Monte Carlo simulation in the probabilistic approach enabled the calibration of the haircut according to a predefined confidence level, confirming the pattern observed in the deterministic framework. The combined evidence strengthens the empirical robustness of the model and highlights the importance of locational and cyclical dynamics in collateral valuation. Full article

Peri-urbanization in rapidly growing cities of the Global South is increasingly driven not only by demographic growth but by escalating inner-city land and housing prices that push households and developers toward peripheral zones. Bangalore exemplifies this transition, where housing affordability pressures, speculative real estate investment, and weak land governance interact to transform agricultural landscapes into fragmented built-up clusters. Using satellite imagery (1991–2024), census data, and GIS-based land-use classification, this study quantifies peri-urban expansion across eight clusters in the Bangalore Metropolitan Region. The results show rapid built-up growth, agricultural land decline, and increasing spatial fragmentation, reflecting processes of extended urbanization beyond formal city boundaries. These transformations produce environmental stress, infrastructure deficits, and socio-spatial inequalities. The paper situates Bangalore within planetary urbanization debates and argues that peri-urban sustainability depends on land market regulation, spatial planning capacity, and data-driven governance. Full article

We use the hedonic price model to measure the effect of school quality on apartment rent prices in Porto Alegre, Brazil. A spatial autoregressive regression (SAR) was employed due to the spatial nature of the data. We estimated the effect of school quality on apartment prices for public and private schools separately. The results shed light on the relation between school quality and apartment prices in a Global South context. We showed that both public and private school quality is valued in Porto Alegre house markets, although the effect is quite different for each type of school. For public schools, the major effect comes from the distance of the nearest schools. An increase in test scores by one standard deviation raises apartment rent prices by 2.7% for the whole city. However, this effect is bigger for some submarkets, reaching 11.6% for the distant suburbs. For private schools, the same effect occurs but for a larger distance radius. The same increase in average test score out to a 2 km distance from private schools raised the apartment price by 1.0%. Nevertheless, this effect reaches 6.6% in one specific submarket. Full article

Seasonality has traditionally shaped the U.S. housing market, with activity peaking in spring-summer and declining in autumn-winter. However, recent disruptions, particularly those following COVID-19, raise questions about shifts in these patterns. This study analyzes housing market data (1991–2024) to examine evolving seasonality and regional heterogeneity. Using Housing Price Index (HPI) data, inventory, and sales data from the Federal Housing Finance Agency and U.S. Census Bureau, seasonal components are extracted via the X-13-ARIMA procedure, and statistical tests assess variations across regions. The results confirm seasonal fluctuations in prices and volumes, with recent shifts toward earlier annual peak (March–April) and amplified seasonal effects. Regional variations align with differences in climate and market structure, while prices and sales volumes exhibit in-phase movement, suggesting thick-market momentum behaviour. These findings highlight key implications for policymakers, realtors and investors navigating post-pandemic market dynamics, offering insights into the timing and interpretation of housing market activities. Full article

Intermediaries are central to complex transactions. In housing markets, real estate brokers coordinate information flows, reduce search costs, and guide lay buyers and sellers through legal and financial steps. Despite this importance, scholarship on brokerage is dispersed across disciplines and methods. This paper presents a semi-systematic review of peer-reviewed articles published between 1970 and 2021. We map (i) study characteristics (country of origin and field), (ii) the distribution of units of analysis (individual, firm/organization, market), and (iii) the most frequently examined topics. Our synthesis indicates steadily rising academic interest but a fragmented knowledge base. We conclude by highlighting gaps—especially the scarcity of cross-country comparisons and the relative lack of qualitative and mixed-method studies on brokers’ practices and experiences. Full article

The housing deficit in developing countries is a common challenge, primarily impacting low-income populations. This paper investigated interinstitutional workflows using Building Information Modelling (BIM) as a social technology to improve the efficiency of design and construction stages in social housing projects. Following a systematic literature review, process maps were developed and applied in a case study within a Brazilian urban community, located in a coastal city with a demographic density of 3602 inhabitants per square kilometre, involving a collaboration framework between a university and municipal authorities. Based on the party’s collaboration and precise cost estimation, the results indicate that this BIM-enabled collaboration supports the governmental decision-making process and leads to more effective resource management and optimised design costs, mainly during the design and construction phases. Therefore, this study concludes that digital modelling workflows are a powerful strategy for developing social housing projects because they facilitate the inclusion of families in the design and decision-making processes. Expanding this approach through integration with geospatial and public agency data is a promising area for future research, using such models in risk assessment policies and city urban planning. Full article

Housing price indices (HPIs) are employed to assess the impact of the business cycle, monetary policy, housing policies, and local market dynamics. However, comparative empirical analysis of different HPI methodologies has not been conducted to measure why or when they may diverge and whether these differences are meaningful. Two leading US HPI choices, the repeat-sale transactional (S&P Case–Shiller) and characteristic-based hedonic (Zillow) indices, although highly correlated, generate different distributions and time-series properties primarily at the city level. The spread between these two HPI choices measures the difference between housing market transaction intensity and a willingness-to-pay characteristic valuation. We find that transactional indices are more volatile, with HPI spreads associated with both macro and local drivers. The transactional index will rise more rapidly in a market with increased buying (positive macro and local market conditions) and fall further in a market with increased selling (negative macro and local market conditions) relative to a hedonic index. A buyer- or seller-biased spread between a transactional and hedonic housing price index (HPI) may impact policy judgments during housing market extremes. Full article

Location effects play a crucial role in the real estate market, encompassing aspects of accessibility and neighborhood quality. While traditional measures exist for accessibility, evaluating neighborhood quality can be a complex task. Understanding these elements is essential for accurately estimating property values, whether for commercial or tax purposes. Recently developed methods based on web scraping and automatic detection using artificial intelligence have proven effective but require substantial human and financial resources, often unavailable in small cities. As a solution, this study proposes and evaluates a simpler mechanism for assessing neighborhood quality using Google Street View images and a scoring system in a human-centered approach. Based on image interpretation, a set of weights is assigned to each point, resulting in a micro-neighborhood quality assessment. This study was conducted in three Latin American cities, and the resulting variable was integrated into hedonic price models. The findings demonstrate the feasibility and effectiveness of the proposed approach. The novelty of this study lies in applying a method based on quasi-objective criteria and adapted to cities with limited technological resources. Full article

The paper contributes to the debate on the holistic sustainability assessment of real estate projects, integrating economic, financial, environmental, and social aspects. A methodological study is presented to support decision-making processes involving the preferability ranking of alternative investment scenarios: new building production vs. retrofitting the existing stock, in the context of urban transformation interventions. The study integrates life cycle approaches by introducing the social components besides the economic and environmental ones. Firstly, a composite unidimensional (monetary) indicator calculation is illustrated. The sustainability components are internalized in the NPV calculation through a Discounted Cash-Flow Analysis (DCFA). Life Cycle Costing (LCC) and Life Cycle Assessment (LCA) are suggested to assess the economic and environmental impacts, and the Social Return on Investment (SROI) to assess the intervention’s extra-financial value. Secondly, a methodology based on multicriteria techniques is proposed. The Hierarchical Analytical Process (AHP) model is suggested to harmonize various performance indicators. Focus is placed on the criticalities emerging in both the methodological approaches, while highlighting the relevance of multidimensional approaches in decision-making processes and for supporting urban policies and urban resilience. Full article

Using panel data on 99 Italian provinces in the period between 2005 and 2020, the research investigates the effects of fundamental economic factors on the home sales at the provincial level, in order to build a forecasting model using a non-linear artificial intelligence approach (MLP-Multiple Linear Perceptron neural network). There are multiple objectives to this: (a) to test the hypothesis that national, regional and local fundamentals such as interest rates, income, inflation rate, unemployment and demography affect the activity’s degree of the housing market; (b) to verify the effectiveness of a neural network in describing the dynamics of the real estate market; (c) to build a simulation model capable of predicting the effect of changes in fundamentals, also due to economic policy measures, on the market. Empirical results show that neural networks offer better capabilities than linear models in representing the complex relationships between the economic situation and the real estate market. The study provides useful information for regulators to improve the effectiveness of monetary policy to stabilize real estate markets as well as for stakeholders to draw up scenarios of market development. Full article

We present empirical evidence on the sensitivity of housing demand in Chile to changes in mortgage interest rates, focusing on units priced between CLF 2000 and 4000 (approximately USD 80,000 to 160,000). This sector, which comprises nearly two-thirds of the country’s housing supply, has experienced a significant decline in sales since 2021. Given its size and responsiveness, it represents a key target for policy measures aimed at reactivating the Chilean real estate market, such as demand-side subsidies for middle-income households. Using impulse response functions derived from vector autoregressive (VAR) and semi-structural models estimated via Bayesian methods with Markov Chain Monte Carlo (MCMC) simulations, we find that a 100-basis-point increase in mortgage rates leads to an average annual decline of 18% in housing sales during the first quarter after the shock. This effect results in a cumulative decline of approximately 57% by the end of the first year. A comparable reduction in mortgage rates yields a symmetrical response. Finally, we offer a linear extrapolation of potential impacts under a hypothetical 200-basis-point decrease in mortgage rates. Full article

From 31 August 2022 to early 2024, the City of Chicago welcomed nearly 40,000 migrants. Chicago had designated itself as a sanctuary city nearly 40 years ago and has since been a popular destination for migrants, accepting large numbers in other periods throughout its history. However, the influx during the period 2022–2024 was unique because of the large amounts of resources local and federal governments dedicated to settling these individuals. Immigrant benefits varied over this period but peaked at $15,000 per family, which did not include services offered by local churches and private organizations. In this study, log-linear multiple regression was employed to determine the impact subsidies can have on the local rental real estate market. According to the study findings, rental real estate rates increased by up to 5.6% in response to subsidization of migrant housing. Additionally, neighborhoods that were adjacent to migrant shelters experienced the greatest additional increase of 29.96%. In addition to the rapidity with which rental real estate pricing can respond to subsidies and policy shifts, the study findings demonstrate the financial benefits that can accrue to real estate owners and managers who participate in the rental marketplace with subsidization. Full article