Real Estate Data Research Articles

Population estimation beyond counts-Inferring demographic characteristics.

Mapping population distribution at a fine spatial scale is essential for urban studies and planning. Numerous studies, mainly supported by geospatial and statistical methods, have focused primarily on predicting population counts. However, estimating their socio-economic characteristics beyond population counts, such as average age, income, and gender ratio, remains unattended. We enhance traditional population estimation by predicting not only the number of residents in an area, but also their demographic characteristics: average age and the proportion of seniors. By implementing and comparing different machine learning techniques (Random Forest, Support Vector Machines, and Linear Regression) in administrative areas in Singapore, we investigate the use of point of interest (POI) and real estate data for this purpose. The developed regression model predicts the average age of residents in a neighbourhood with a mean error of about 1.5 years (the range of average resident age across Singaporean districts spans approx. 14 years). The results reveal that age patterns of residents can be predicted using real estate information rather than with amenities, which is in contrast to estimating population counts. Another contribution of our work in population estimation is the use of previously unexploited POI and real estate datasets for it, such as property transactions, year of construction, and flat types (number of rooms). Advancing the domain of population estimation, this study reveals the prospects of a small set of detailed and strong predictors that might have the potential of estimating other demographic characteristics such as income.

Polarized Paths: ‘Selling’ Cycling in City and Suburb

ABSTRACTWhile cycling infrastructure is increasingly integrated into North American cities, bike lanes are still met with considerable resistance. Contradictory housing concerns that bike lanes will either lower property values or spur gentrification are central to this ‘bikelash.’ Our research explores the ways in which cycling infrastructure is part of the development and consumption of housing and real estate in a growing mid‐sized region. Instead of analysing real estate data, we engage with real estate agents and developers to provide new insights into how cycling is ‘sold’ and marketed in both the home‐building and home‐buying processes. Central to this discussion is the stark difference between core urban areas, where the built environment is more conducive to cycling, and automobile‐oriented suburbs. Through this dichotomy, we examine differences based on demographics, as well as the active role that realtors and developers play in selling cycling as transportation, lifestyle, and recreation.

Drivers and constraints of land use transitions on Western grasslands: insights from a California mountain ranching community

ContextLand use change drives a host of sustainability challenges on Earth’s grasslands. To understand the relationship between changing land use patterns, human well-being, and ecosystem services, research is needed into land use transitions on privately-owned grasslands. Such inquiry lies at the intersection of land system science, landscape sustainability science and environmental governance.ObjectivesThis study investigated land use change in a mountain ranching community in the Sierra Nevada, California. The research objective was to highlight factors influencing land use transitions and corollary ecological outcomes on privately-owned grasslands in the Western US.MethodsThis mixed methods case study integrated participant observation, 30 semi-structured interviews, and analysis of land cover and real estate data. Interviews were conducted with ranchers, public agencies, and conservation and real estate industry representatives, and analyzed with the constant comparison method using NVivo 12.ResultsLand use transitions in the case study region include agricultural intensification, residential and solar development, and disintensification. These transitions were influenced by many factors including decreasing land access and water availability, amenity migration, intergenerational succession, and conservation policy.ConclusionsBy highlighting factors influencing land use transitions on working lands, this study can be applied to improve the uptake of environmental policies. For the future, several approaches may support grasslands conservation: ensuring grazing lands access, income diversification, groundwater regulations, agriculture-compatible conservation easements, and land use policies supporting ownership transition to amenity purposes rather than low-density residential development.Supplementary InformationThe online version contains supplementary material available at 10.1007/s10980-021-01385-6.

An End-to-End Named Entity Recognition Platform for Vietnamese Real Estate Advertisement Posts and Analytical Applications

The volume and complexity of publicly available real estate data have been snowballing. As a result, information extraction and processing have become increasingly challenging and essential for many PropTech (Property Technology) companies worldwide. The challenges are even more pronounced with languages other than English, such as Vietnamese, where few studies in this field have taken place. This paper presents an end-to-end framework for automatically collecting real estate advertisement posts from different data sources, extracting useful information, and storing computed data into proper data warehouses and data marts for the Vietnamese advertisement posts in real estate. After that, one can serve aggregated data for other descriptive and predictive analytics. We combine two models for constructing the most appropriate extraction step: Noise Filtering and Named Entity Recognition (NER). These models can help process initial input data and extract all helpful information. The experiment results show that using PhoBERT_<i>large</i> can achieve the best performance compared to other approaches. Furthermore, we can obtain the corresponding F1 scores of the Noise filtering module and the NER module as 0.8697 and 0.8996, respectively. Finally, we utilize Superset for implementing analytic dashboards to visualize the predicted results and serve for further analysis and management processes.

Mathematical justification on the origin of the sigmoid in logistic regression

Logistic regression is a commonly used classification algorithm in machine learning. It allows categorizing data into discrete classes by learning the relationship from a given set of labeled data. It learns a linear relationship from the given data set and then introduces nonlinearity through an activation function to determine a hyperplane that separates the learning points into two subclasses. In the case of logistic regression, the sigmoid is the most used activation function to perform binary classification. The choice of sigmoid for binary classifications is justified by its ability to transform any real number into a probability between 0 and 1. This study provides, through two different approaches, a rigorous mathematical answer to the crucial question that torments us, namely where does this logistic function on which most neural network algorithms are based come from? References Stoltzfus, "Logistic regression: A brief primer," Academic Emergency Medicine, vol. 18, no. 10, pp. 1099-1104, 2011. Peng et al, "An introduction to logistic regression analysis and reporting," The Journal of Educational Research, vol. 96, no. 1, pp. . Costa et al, "A logistic regression model for consumer default risk," Journal of Applied Statistics, vol. 47, no. 13-15, pp. 2879-2894, 2020. Gatzert and M. Schubert, "Cyber risk management in the us banking and insurance industry: A textual and empirical analysis of determinants and value," Journal of Risk and Insurance, vol. 89, no. 3, pp. 725-763, 2022. Premsmith and H. Ketmaneechairat, "A predictive model for heart disease detection using data mining techniques," Journal of Advances in Information Technology, vol. 12, pp. 14-20, 2021. Almotiri et al, "Using api with logistic regression model to predict hotel reservation cancellation by detecting the cancellation factors," International Journal of Advanced Computer Science and Applications, vol. 12 , no. 6 , pp. . Kudupudi et al, "Spam message detection using logistic regression," International Journal of Advanced Computer Science and Applications, vol. 9, no. 9, pp. 815-818, 2021. Keren and . Cuiwei, "Housing price analysis using linear regression and logistic regression: A comprehensive explanation using melbourne real estate data," in 2021 IEEE International Conference on Computing (ICOCO), 2021, pp. 241-246. Dheeru and G. Casey, "UCI machine learning repository," 2017. [Online]. Available: http://archive.ics. uci.edu/ml Goldbloom, "Kaggle dataset," 2010. [Online]. Available: https: //www.kaggle.com/ Febrianti et al, "The parameter estimation of logistic regression with maximum likelihood method and score function modification," Journal of Physics: Conference Series, vol. 1725, no. 1, p. 012014, 2021. Lucena, "Loss functions for classification using structured entropy," 2022. [Online]. Available: https://arxiv.org/abs/2206.07122 Hikmat and A. Abdulazeez, "Comparison of optimization techniques based on gradient descent algorithm: a review," PalArch?s Journal of Archaeology of Egypt/Egyptology, vol. 18, no. 4, pp. 2715-2743, 2021.E. Norton et al, “Odds ratios-current best practice and use,” Journal of the American Medical Association, vol. 320, no. 1, pp. 84–85, 2018 Tong, Fundamental Properties and Sampling Distributions of the Multivariate Normal Distribution. Springer New York, 1990, pp. 23– 61.

Use of Google Trends to Predict the Real Estate Market: Evidence from the United Kingdom

This paper demonstrates how Google Trends data can be used to improve real estate market predictions. Online searches produce valuable data that precede economic decisions. This study explores the usefulness of Google search engine data in predicting the real estate markets. The results indicate that Google data can be an additional source of information for investors and policymakers. This analysis adds to the existing literature that explores the role of behavioral factors in the decision-making process. Google Trends data are identified as an important predictor of real estate market prices and sales volume.

CADASTRAL REGISTRATION OF REAL PROPERTY WITH DATA DIGITALIZATION

Problem statement. The transition in Ukraine from registration and accounting of land in the State Land Cadastre to registration and accounting of real estate in the multi-purpose cadastre requires research aimed at optimizing the information of the multi-purpose cadastre and the form of data representation based on their digitalization to limit the size of the database by technological support. The composition and scope of real estate accounting information data determine the purpose and functions of the multi-purpose cadastre. The problem is the huge amount of information about real estate and the great variety of objects. The difficulty of formalizing too much data for a multi-purpose cadastre information system makes it necessary to explore ways to reduce the amount of software memory involved by digitizing the data. Purpose of the article. Solving the problem of reducing the amount of memory for the database of registration and accounting of real estate through digitalization requires research on the composition of the necessary information about real estate in the multi-purpose cadastre to ensure the functions of the cadastre based on analysis of users' needs. In order to move from the information on real estate determined by the results of analysis to the basic and thematic geospatial data of the cadastre, it is necessary to perform multilevel structuring of cadastral objects at the level of real estate classification, including land plots, construction objects by characteristic legal, technical and value features. A significant reduction in the amount of memory used in the database of information technology support of the multi-purpose cadastre was achieved by coding the characteristics of real estate, including land, construction objects and other land improvements that are part of real estate. Conclusion. Digitization of real estate data in the multi-purpose cadastre allows you to: significantly reduce the amount of database memory used on the server; provide easy access to data on real estate properties; significantly increase the protection of identification of cadastral objects and their properties; opens new opportunities for real estate management, control over compliance with the law, the application of targeted measures to stimulate the desired development of real estate and prevent adverse use of territories.

The economics of thermal superinsulation in buildings

In comparison to conventional thermal insulators, superinsulation materials (SIMs), such as silica aerogel or vacuum insulation panels, provide a similar insulation performance at half to a quarter of the material thickness but this superior thermal insulation performance typically comes at a significantly higher material cost. However, under certain conditions, the use of superinsulation materials in building walls allows for the creation of additional floor space.Here, we derive a simple equation to quantify the cost to create such additional space using superinsulation materials as opposed to conventional thermal insulators. The equation has six independent variables, namely the thermal conductivity and cost of the superinsulation and conventional insulation materials, as well as two building geometry parameters. Notably, the cost to create additional floor space is independent of the heat transfer coefficient (U-value) of the wall.The real estate price distributions within major cities around the world are presented in order to compare the cost to create additional space with the potential financial benefit.The analysis of typical construction types, combined with the real estate data, shows that, from a financial perspective, the use of superinsulation such as silica aerogel or vacuum insulation panels (VIPs) is already clearly profitable in several major cities globally. Improvements of the production processes of superinsulation materials and the associated reduction in costs will be key drivers to make superinsulation materials economically feasible for many other locations in the future.

AOI-shapes: An Efficient Footprint Algorithm to Support Visualization of User-defined Urban Areas of Interest

Understanding urban areas of interest (AOIs) is essential in many real-life scenarios, and such AOIs can be computed based on the geographic points that satisfy user queries. In this article, we study the problem of efficient and effective visualization of user-defined urban AOIs in an interactive manner. In particular, we first define the problem of user-defined AOI visualization based on a real estate data visualization scenario, and we illustrate why a novel footprint method is needed to support the visualization. After extensively reviewing existing “footprint” methods, we propose a parameter-free footprint method, named AOI-shapes, to capture the boundary information of a user-defined urban AOI. Next, to allow interactive query refinements by the user, we propose two efficient and scalable algorithms to incrementally generate urban AOIs by reusing existing visualization results. Finally, we conduct extensive experiments with both synthetic and real-world datasets to demonstrate the quality and efficiency of the proposed methods.

The Creation and Performance Implications of Firm-Level Human Capital Resources

We investigate how the degree of alignment between individual and firm-level human capital resources influences performance. We argue that a high degree of alignment between firm and individual-level human capital profiles increases human capital utilization, coordination, and human capital transfer. This consequently improves performance, and the benefits increase with firm size. For nascent firms, this alignment is created through similarity of individual-level human capital profiles. Drawing on Utah residential real estate data from 1996-2014 and using novel measures to dynamically capture individual- and firm-level human capital profiles, we find that brokerages with higher brokerage-agent human capital alignment represent more home sellers and buyers than brokerages with lower alignment. These benefits increase with firm size. We also find that agent-agent human capital similarity in the first year significantly influences brokerage-agent human capital alignment (and consequently performance) in subsequent years. These results suggest that managers from founding onward must carefully craft and manage firm-level human capital resources to ensure high levels of alignment and utilization. Firms that better manage their general human capital may enjoy persistent performance advantages that are resistant to turnover and difficult for competitors to replicate.

A note on real estate appraisal in Brazil

Abstract Brazilian banks commonly use linear regression to appraise real estate: they regress price on features like area, location, etc, and use the resulting model to estimate the market value of the target property. But Brazilian banks do not test the predictive performance of those models, which for all we know are no better than random guesses. That introduces huge inefficiencies in the real estate market. Here we propose a machine learning approach to the problem. We use real estate data scraped from 15 thousand online listings and use it to fit a boosted trees model. The resulting model has a median absolute error of 8.16%. We provide all data and source code.

Development of an Ontology-Based Visual Approach for Property Data Analytics

Real estate is a complex market that consists of many layers of social, financial, and economic data, including but not limited to price, rental, location, mortgage, demographic and housing supply data. The sheer number of real estate properties around the world means that property transactions produce an extraordinary amount of data that is increasing exponentially. Most of the data are presented through thousands of rows on a spreadsheet or described in long paragraphs that are difficult to understand. The emergent data visualization techniques are intended to allow data to be processed and analytics to be displayed visually to enable an understanding of complex information and the identification of new patterns from the data. However, not all visualization techniques can achieve such a thing. Most techniques are able to display only visual low-dimensional data. This paper introduces an ontology visualisation methodology to explore the ontologies of property data behaviour for multidimensional data. The visualisation combines real estate data statistical analysis with several high dimensional data visualisation techniques, including parallel coordinates and stacked area charts. By using six residential suburbs in Sydney as a demonstration, we find that the developed data visualisation methodology can be applied effectively and efficiently to analyse complex real estate market behaviour patterns.

Development of a digital service for real estate transactions

The majority of present-day aggregators of the Russian real estate market fail to meet modern requirements and trends. Currently, the information support of real estate valuation activities is generally assigned to individual values, rather than the valuation community as a whole. The absence, insufficiency, unreliability of the market information makes it difficult to determine the cadastral value of the properties as well fulfill the requirements prescribed by the existing methodological recommendations. The main problem in developing digital platforms is that the value of the digital platform proposition can only be adequately assessed by the platform developer, while the complexity of creating a quality digital platform may exceed the benefits for the developer. In this regard, we set a goal to analyze the aggregators of the real estate market in terms of the shortcomings, whose systematization is to lay the basis for a consolidated real estate market database of Russian Federation. In this article, selected digital platforms were analyzed with regards to meeting specified criteria using a multi-criterial rating system. The results of the study represent the necessary criteria, conclusions concerning compliance with certain criteria based on the analysis of classifieds, as well as recommendations for the use of innovative technologies to ensure the most advanced operation of real estate market aggregators. In addition, several forms of information exchange between market players and viable solutions to common problems are suggested. A method of developing a consolidated real estate market database was developed. It is based on innovative information technologies and the actionable way of implementing software solutions designated for automation and structuring of real estate data.

Real Estate Data Marketplace

Real estate financing, construction, and management are being revolutionised by the data science and infrastructure technologies of Artificial Intelligence (AI), Internet of Things (IoT), Big Data, Digital Object Identifiers (DOI) and Blockchain. The key to automation and integration is a Real Estate Data Marketplace across the lifespan of finance, planning, construction, regulation, management, even refurbishment and demolition. Integration of digital 4.0 and industry 4.0. Real estate is becoming increasingly digital, automated and integrated; embracing connected-buildings, wearable personal devices, integrated transportation systems, buildings and infrastructure data management and smart cities. The key to promoting the use of data-driven techniques in the real estate sector is the introduction of a Data Marketplace that promotes validation of data and tokenisation to create value for the owners of the data, Blockchain security and governance for users of the data, the application of Artificial Intelligence for data analytics and ethics for governance. The technical capability exists today for a complete end-to-end reshaping of the real estate market based on data and ethics. This is data-driven real estate (cf. Google, Amazon, Alibaba, Tencent). The contributions of this review paper are fourfold: (a) to provide a vision of a fully digital real estate marketplace; (b) to brief the industry on digital technology and also stimulate engagement with the computer science community; (c) to encourage debate amongst professionals, academics and politicians of the benefits of full automation and integration of real estate; (d) present ethics for the Real Estate Data Marketplace based on lawfulness, fairness and transparency.

A Downside Risk Analysis of Inflation Hedging Capabilities of Individual Assets and Optimal Asset Allocation

The objective of this study is to examine the inflation hedging capabilities of most widely used asset classes in Pakistan. It also attempts to find out the possibility of creating an inflation protected optimal asset mix. The sample consists of monthly data of cash, gold, stocks, foreign currency, real estate and inflation from 2005 to 2015. The major sources of data are SBP, World Bank and Pakistan Statistics Bureau. The downside analysis of these assets concludes that cash act as an inflation hedge for all the investment horizons. The findings showed that the Gold and stocks also have inflation hedging abilities in short run which extend to medium term investment horizon for gold only, while stocks appear to be a good inflation hedge for longer investment horizons. This study also suggests that investors can strategically create optimal portfolios that are hedged against inflation.

Do Large Gains Make Willing Sellers?

AbstractUsing unique real estate data that allow for accurately measured capital gains, we examine whether sell propensities depend on the magnitude of a seller’s capital gain. We find that short-term sell propensities are flat over losses and increasing in gains. Consistent with their higher sell propensities, selling prices are lower for properties with larger gains. Large-sized short-term stock investments also have sell propensities that are flat over losses and increasing in gains, although the sell propensities of typical-sized short-term stock investments are V-shaped. Our findings provide empirical support for theories of realization utility.

Improving the Technology for Implementing a 3D Cadastre in Existing Accounting Information Systems

In the Russian Federation, the issue of improving the cadastral system is currently more relevant than ever. This is determined by the complication of the procedure for designing and building the cadastral real estate objects. Modern architecture is becoming more complex and diverse year-by-year. The configuration of the construction facilities is becoming more increasingly complex, and these days, they can be built not only on the ground surface but also above or under the ground. In practice, such design solutions lead to uncertainty and ambiguity of their routine cadastral registration, and these objects are registered according to their two-dimensional projection on the ground. Currently, almost all design agencies use 3D simulation in solving issues related to the design, construction, and sale of both industrial or agricultural facilities and residential or office buildings and apartments. Leading Krasnodar enterprises engaged in the design of various real estate objects use three-dimensional models in providing customers with the complete scope of work. The paper authors reveal the basic concepts of a three-dimensional cadastre in a modern system of engineering, design, construction, and architecture. The prerequisites for switching to the 3D cadastre have been considered, the cadastral registration aspects specified, and the issues concerning three-dimensional representation and processing 3D real estate data discussed. The main 3D data representation models are listed.

ABOUT CONSTRUCTION OF A UNIFIED INFORMATION ADDRESS SYSTEM OF UKRAINE

The problem of Address registers of settlements according to uniform rules and single a unified State information address system is acute on the agenda in the last decade. Addresses are a component of many cadasters and registers that have been created and operate in Ukraine today. The problem of creating the Unified Address system of Ukraine is exacerbated in the conditions of accelerated digital transformation of public relations. The analysis of recent research and publications allowed to characterize the state of creation of the Unified Address Register of Ukraine as unsatisfactory, revealed shortcomings and lack of a common vision of aspects of addressing issues. A new comprehensive solution to the problems of targeted issues is proposed - the construction of a single unified State information address system. Substantiated and presented common approaches, understandings, definitions, structure and relations of address data are the conceptual provisions of the construction of a single unified State information address system and the basis for the development, approval, adoption at the legislative level. The construction of a conceptual model of address data is based primarily on the internationally established specifications of address data used in Infrastructure for Spatial Information in the European Community (INSPIRE) and the National Geospatial Data Infrastructure of Ukraine. The address system is defined as an information system, that consists of a set of interacting four structural components: 1) addresses, 2) a single address register, 3) address points, 4) address electronic services. The address system performs the functions of identifying the object of addressing, identifying the location of objects of addressing, ensuring the interaction of registers, creating an information address resource of the state, mapping the object of addressing, providing search for the location of the object of addressing. The concept proposes to use the Geographical Identifier of real estate objects of the established structure and addresses, which creates conditions for joint processing of real estate data in geographic information systems and the introduction of a single address register.

Economic aspects of land use in the Kyiv and suburban areas

In the article, the author has focused on analyzing the current state of land use by types of enterprises’ economic activity, regional economic and financial data to propose a new robust model for cost-effective land use planning for commercial and non-commercial enterprises. The research results can serve as an important material for the decision-making process on how to develop the land and the city areas in the context of new global economic development. It provides extensive overview of existing land use trends for Kyiv city based on analytical data and scientific assumptions. The author believes that this research will be beneficial for government organizations, local government authorities, international organizations, private institutions, and researchers. The goal of the research paper is to build a solid scientific model based on a general understanding of underlying economic challenges of efficient land use considering past data, short-term and long-term planning. The paper has an overview of city planning documentation and city statistical data in the context of real estate, urban population, economic data, including research of real estate and currency exchange rate data to median salary in Kyiv starting from the 2000s. It is important not to put too much focus on the existing models and systems, as they rely too much on the assumptions and complicated calculations that are hard to make use of in real-world planning. Instead, we build our research on real-world data and developed a forecast for the size of investment in land use, average real estate prices for the next 5 years. The paper noted an existing problem of inconsistency of the existing norms and regulations in Ukraine concerning rational and effective land use and planning, especially for local authorities and commercial organizations. The author substantiates why the economy in the context of urbanization needs a new look. The paper uses the planning of Kyiv city. It is a suitable example of a developing city, so the proposed model can be developed based on the city’s economic and land use data. This research can help solve the existing problems of urbanization in Ukraine and have a positive impact on the economic development of the city and the region.

The Complex Neural Network Model for Mass Appraisal and Scenario Forecasting of the Urban Real Estate Market Value That Adapts Itself to Space and Time

In the modern scientific literature, there are many reports about the successful application of neural network technologies for solving complex applied problems, in particular, for modeling the urban real estate market. There are neural network models that can perform mass assessment of real estate objects taking into account their construction and operational characteristics. However, these models are static because they do not take into account the changing economic situation over time. Therefore, they quickly become outdated and need frequent updates. In addition, if they are designed for a specific city, they are not suitable for other cities. On the other hand, there are several dynamic models taking into account the overall state of the economy and designed to predict and study the overall price situation in real estate markets. Such dynamic models are not intended for mass real estate appraisals. The aim of this article is to develop a methodology and create a complex model that has the properties of both static and dynamic models. Moreover, our comprehensive model should be suitable for evaluating real estate in many cities at once. This aim is achieved since our model is based on a neural network trained on examples considering both construction and operational characteristics, as well as geographical and environmental characteristics, along with time-changing macroeconomic parameters that describe the economic state of a specific region, country, and the world. A set of examples for training and testing the neural network were formed on the basis of statistical data of real estate markets in a number of Russian cities for the period from 2006 to 2020. Thus, many examples included the data relating to the periods of the economic calm for Russia, along with the periods of crisis, recovery, and growth of the Russian and global economy. Due to this, the model remains relevant with the changes of the international economic situation and it takes into account the specifics of regions. The model proved to be suitable for solving the following tasks: industrial economic analysis, company strategic and operational management, analytical and consulting support of investment, and construction activities of professional market participants. The model can also be used by government agencies authorized to conduct public cadastral assessment for calculating property taxes.