Conference PaperPDF Available

Artificial intelligence in real estate market analysis

Authors:

Abstract

Real estate has always been an important investment opportunity. With a diverse set of financial instruments linked to real estate assets, it is significant for both investors and intermediaries. In this paper we assess how artificial intelligence can be used to improve our understanding for the real estate market changes. We suggest and test a three-stage model in support for real estate valuation and market forecasting, that is able to account for global economic factors as well as for individual characteristics influencing property prices. Every stage provides for using different artificial intelligence and machine learning methods in order to automate processing of market data and assess how qualitative factors affect valuation. We conduct a survey on the accuracy of the model NAREIT and BGREIT index data.
... La inversión en el sector inmobiliario ha sido históricamente una oportunidad crucial. Dado el variado conjunto de instrumentos financieros relacionados con activos inmobiliarios, su importancia es significativa tanto para los inversores como para los intermediarios (Kabaivanov & Markovska, 2021). En este contexto, la inteligencia artificial emerge como una herramienta estratégica fundamental para potenciar nuestra comprensión de las dinámicas del mercado inmobiliario. ...
Article
Full-text available
El análisis de los datos es uno de los principales aspectos a considerar para la toma de decisiones en el ámbito social y empresarial. El mercado de bienes raíces es un componente decisivo y de soporte para las economías de los países a nivel mundial. Un análisis de la variación de los precios inmobiliarios a través de series temporales puede facilitar la identificación de mejores oportunidades a los inversores. Esta investigación tiene por objetivo aplicar el método ARIMA para el pronóstico del avalúo de bienes raíces. Se utiliza un enfoque cuantitativo con un diseño de investigación no experimental. Para la minería de datos se aplica el proceso KDD conjuntamente con el proceso de ARIMA para el pronóstico. Entre sus principales resultados se obtiene una base de datos limpia, la cual posteriormente es transformada a una serie estacionaria, para de esta manera ajustar el modelo y aplicar al pronóstico al caso de estudio en la ciudad de Riobamba, Ecuador. Se muestran datos con rangos de confiabilidad al 80% y 95%. El procedimiento detallado en este estudio puede aplicarse a cualquier contexto de predicción de series temporales en el sector de bienes raíces.
... A number of research focused only on the local real estate markets during the pandemic, in e.g. Czech Republic [19], UK [20], Australia [21], Nigeria [22] Poland [23] or South Africa [24]. ...
Article
Full-text available
The work included an analysis of the primary real estate market in Krakow in 2017‑2020. The above analysis was carried out on the basis of transactions obtained from the official register at the city hall. The results of the research made it possible to observe the changes taking place in the market: the prices grew moderately, and the number of transactions was between 8,000 and 11,000 each year. In 2020, due to the COVID-19 pandemic, the number of transactions conducted dropped sharply. Despite the reduced interest of potential buyers, prices per square meter of residential space increased significantly during the period under review. Thus, the pandemic only affected the number of transactions and not the average price per unit of space.
... As firms hurried to adopt remote work due to the COVID-19 pandemic, cybersecurity worries increased, underscoring the urgent need for strong cybersecurity measures in this new digital landscape (Thangaraja, 2022). The author investigates how AI may enhance real estate market analysis and assessment using a three-stage methodology that uses index data to measure accuracy (Kabaivanov, 2021). The significance of government-led digitization initiatives in enhancing regulatory control in financial markets, reducing fraud, and enhancing tax collection effectiveness in order to highlight the significance of government-led digitization initiatives in enhancing regulatory control in financial markets, reducing fraud, and enhancing tax collection effectiveness (Stang, 2023), focuses on the post-2008 regulatory-driven demand for accurate real estate assessments and the role of AI and machine learning in automating and enhancing the valuation process. ...
Chapter
Full-text available
The revolutionary effects of artificial intelligence (AI) and socially responsible marketing on the real estate market are examined in this chapter. Real estate is being redefined by changing consumer values as well as increased social and environmental consciousness. A flexible tool like artificial intelligence (AI) encourages innovation by providing data-driven insights, individualized marketing, and operational efficiencies. The concept simultaneously connects real estate transactions with significant societal and environmental contributions. The investigation starts with the key cause selection process, in which real estate professionals make choices that go beyond transactions and resonate as statements of intent with customers and communities. Forging relationships beyond typical buyer-seller interactions, creating emotionally compelling narratives becomes essential. AI boosts customer experiences, improves relationships, and synchronizes them with client values.
... Analysis of AI technology in real estate. Artificial intelligence in the real estate industry [23][24][25][26] has grown recently as more companies capitalize on its potential to improve efficiency and decision-making. ...
Article
Full-text available
This paper deals with an investigation centered on developing a real estate app on the basis of Artificial Intelligence and Virtual Reality technologies. The study explores the advantages and disadvantages of using Artificial Intelligence and Virtual Reality technologies in real estate. The main focus of the study was on AI/VR applications that have importance for the real estate industry. This paper explains how AI and VR technologies can benefit the real estate market. VR and AI technologies have had a long history in the academic world since the middle of the last century, but not at the same level, due to the lack of large amounts of data and computational power required for both technologies. In recent years, the expansion of IT technologies has helped to remove the technical obstacles, which is why the interest in VR and AI technologies has acutely increased in society and the public over the past several years. Not only the research and abstract ideas of the virtual world but also the feasibility of companies from different industries are becoming more and more relevant. In particular, when it comes to virtual reality, the focus is on 360° images. With special cameras, the entire environment can be captured in a three-dimensional space and then cut together in such a way that the viewer can actually look around in this room and monitor events from his perspective. This opens the possibility of presenting different content in a completely new way. Technical shortcomings currently hamper the feeling of true immersion in virtual worlds. A detailed literature review provides the necessary theoretical basis for artificial intelligence and virtual reality with a particular emphasis on its use in the real estate industry.
Chapter
Forecasting real estate market volatility is essential for investors, developers, and policymakers in the dynamic real estate industry landscape, which can be considered a financial market. This paper extends the discussion of forecasting financial market volatility using machine learning techniques to the real estate market context. Drawing upon insights from relevant research studies, we delve into the diverse methodologies, performance evaluation metrics, and case studies specific to predicting real estate market volatility. Machine learning models, including regression analysis, time series models, ensemble methods, and deep learning networks, are applied to capture the intricate patterns and uncertainties in the real estate market. Economic indicators, investor sentiment, geospatial data, and housing market fundamentals enhance forecasting accuracy. Performance evaluation metrics like Intersection over Union (IoU) and Mean Squared Error (MSE), prove indispensable for evaluating the reliability of predictive models in this domain. The studies presented in this review demonstrate the practical applications of machine learning in forecasting real estate market volatility across diverse regions and property types. By adapting methodologies from the broader financial market context, we provide valuable insights for stakeholders seeking to make informed decisions in the ever-evolving real estate financial market.
Article
Full-text available
Aim: In the conducted research, profiles of seasonality in the housing market were determined, which provided an opportunity to answer two fundamental questions: what is the nature of harmonic variation in the seasonality and periodicity of the studied components of the construction process? what parameters of the ARIMA model optimally describe the construction market? Methodology: In the conducted research, using the X13-ARIMA-SEATS model, seasonal decomposition was carried out in the various stages of the housing construction process. Results: The research process conducted to identify seasonal fluctuations in the housing construction market showed that harmonic fluctuation profiles can be identified on an annual basis. An analysis of seasonal fluctuations was carried out for each of the three stages of the housing construction process, while also checking how these profiles function for Poland in general, and for individual investors, and for those building apartments for sale or to rent. The study showed that the market for real estate development activity differs in its seasonal characteristics from that of individual investors. Implications and recommendations: The conclusions obtained from the research can provide support in the decision-making process, both from a macro and microeconomic perspective. Parameterisation of the occurring fluctuations, and taking them into account in the process of developing a forecast can provide decision-making rationale in the implementation of macroprudential and financial stability policies Originality/Value: A novelty is in the demonstration that the residential real estate market in Poland shows different seasonal parameters, divided into the market of individual investors and investors who build apartments for sale or rent.
Preprint
Full-text available
The article presents a Multivocal Literature Review (MLR) on the use of Artificial Intelligence (AI) in the real estate sector, aiming to analyze existing applications, literature gaps, and current challenges. The methodology involved defining keywords, searching online repositories, and applying inclusion/exclusion criteria. In total, 185 documents were selected and reviewed. Findings underscore the significance of areas such as personalized strategies for clients, real estate recommendation systems, and process automation. A literature gap was identified regarding the analysis of performance and accuracy of these applications, indicating the need for further research and technological development to meet the demands of the real estate sector.
Article
Full-text available
У статті розкрито особливості розвитку ринку нерухомості у взаємозв’язку з динамікою економічних процесів. Основною метою дослідження є встановлення впливу ринків нерухомості на зміни в економіці країн світу та України. Критичний аналіз наукових підходів учених сьогодення відносно вирішення проблеми підвищення інвестиційної привабливості та подальшого зростання економіки виявив, що зміст їх наукових публікацій в своїй основі розкриває важливість процесів прийняття рішень у сфері операцій з нерухомістю і вивчення ринків зокрема. Проте, поза увагою лишається вивчення змін, що стосуються не тільки формування інвестиційної привабливості ринків нерухомості, але й більш глибокого вивчення впливу ринку нерухомості на тенденції в економіці країн світу та України. Актуальність представленої наукової проблеми полягає у необхідності вивчення перспективності вкладання капіталу в знерухомлені активи на основі встановлення тенденцій розвитку ринків нерухомості, а також визначення впливу ринку нерухомості на тенденції в економіці країни чи групи країн. Методологічну основу дослідження становить комплекс використаних для отримання кінцевих результатів методів: табличний, аналітичний та порівняння – при формуванні рейтингу інвестиційної привабливості країн світу для іноземних інвесторів; абстрактно-логічний та регресійного аналізу – для розкриття взаємозв’язку розвитку ринку нерухомості та тенденцій в економіці країн світу та України; узагальнення – при зведенні висновків за результатами досліджень. Об’єктом дослідження є світовий ринок нерухомості як сукупність національних ринків, істотно відмінних один від одного асинхронністю розвитку, обсягами інвестування, рівнем цін на нерухомість та ризиків, які супроводжують їх формування. У статті розкрито основні результати застосування наукових методів дослідження для встановлення взаємозв’язку розвитку ринків нерухомості з динамікою економічних процесів. Результати дослідження носять прикладний характер і мають практичну цінність при обгрунтуванні вибору нерухомості в якості об’єкта інвестування.
Article
Full-text available
The article presents a two-stage model for estimating the value of residential property. The research is based on the application of a sequence of known methods in the process of developing property value maps. The market is divided into local submarkets using data mining, and, in particular, data clustering. This process takes into account only a property’s non-spatial (structural) attributes. This is the first stage of the model, which isolates local property markets where properties have similar structural attributes. To estimate the impact of the spatial factor (location) on property value, the second stage involves performing an interpolation for each cluster separately using ordinary kriging. In this stage, the model is based on Tobler’s first law of geography. The model results in property value maps, drawn up separately for each of the clusters. Experimental research carried out using the example of Siedlce, a city in eastern Poland, proves that the estimation error for a property’s value using the proposed method, evaluated using the mean absolute percentage error, does not exceed 10%. The model that has been developed is universal and can be used to estimate the value of land, property, and buildings.
Article
Full-text available
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.
Article
Full-text available
Understanding the pattern of financial activities and predicting their development and changes are research hotspots in academic and financial circles. Because financial data contain complex, incomplete and fuzzy information, predicting their development trends is an extremely difficult challenge. Fluctuations in financial data depend on a myriad of correlated constantly changing factors. Therefore, predicting and analysing financial data are a nonlinear, time-dependent problem. Deep neural networks (DNNs) combine the advantages of deep learning (DL) and neural networks and can be used to solve nonlinear problems more satisfactorily compared to conventional machine learning algorithms. In this paper, financial product price data are treated as a one-dimensional series generated by the projection of a chaotic system composed of multiple factors into the time dimension, and the price series is reconstructed using the time series phase-space reconstruction (PSR) method. A DNN-based prediction model is designed based on the PSR method and a long- and short-term memory networks (LSTMs) for DL and used to predict stock prices. The proposed and some other prediction models are used to predict multiple stock indices for different periods. A comparison of the results shows that the proposed prediction model has higher prediction accuracy.
Article
Full-text available
Hedonic prices of landscape are estimated in the urban fringe of Dijon (France). Viewshed and its content as perceived at ground level are analyzed from satellite images supplemented by a digital elevation model. Landscape attributes are then fed into econometric models (based on 2,667 house sales) that allows for endogeneity, multicollinearity, and spatial correlations. Results show that when in the line of sight, trees and farmland in the immediate vicinity of houses command positive prices and roads negative prices; if out of sight, their prices are markedly lower or insignificant: the view itself matters. The layout of features in fragmented landscapes commands positive hedonic prices. Landscapes and features in sight but more than 100–300~m away all have insignificant prices.
Article
It is clear that the learning speed of feedforward neural networks is in general far slower than required and it has been a major bottleneck in their applications for past decades. Two key reasons behind may be: (1) the slow gradient-based learning algorithms are extensively used to train neural networks, and (2) all the parameters of the networks are tuned iteratively by using such learning algorithms. Unlike these conventional implementations, this paper proposes a new learning algorithm called extreme learning machine (ELM) for single-hidden layer feedforward neural networks (SLFNs) which randomly chooses hidden nodes and analytically determines the output weights of SLFNs. In theory, this algorithm tends to provide good generalization performance at extremely fast learning speed. The experimental results based on a few artificial and real benchmark function approximation and classification problems including very large complex applications show that the new algorithm can produce good generalization performance in most cases and can learn thousands of times faster than conventional popular learning algorithms for feedforward neural networks.1
Article
This study constructs an integrated early warning system (EWS) that identifies and predicts stock market turbulence. Based on switching ARCH (SWARCH) filtering probabilities of the high volatility regime, the proposed EWS first classifies stock market crises according to an indicator function with thresholds dynamically selected by the two-peak method. An hybrid algorithm is then developed in the framework of a long short-term memory (LSTM) network to make daily predictions that alert turmoils. In the empirical evaluation based on ten-year Chinese stock data, the proposed EWS yields satisfying results with test-set accuracy of 96.4% and an average of 2.8 days forewarned period. The model’s stability and practical value in the real-time decision-making are also proven by the cross-validation, back-testing and reality check.
Article
The current trend of increasing construction project size and complexity results in higher level of project risk. As a result, risk management is a crucial determinant of the success of a project. It seems necessary for construction companies to integrate a risk management system into their organizational structure. The main aim of this paper is to propose a risk assessment framework using Artificial Neural Network (ANN) technique. Three main phases of the proposed framework are risk management phase, ANN training phase and framework application phase. Thereby, Risk Factors are identified and analysed using Failure Mode and Effect Analysis (FMEA) technique. ANN model is created and trained to evaluate the impact of Risk Factors on Project Risk which is represented through the ratio of contractor’s profit to project costs. As a result, the framework with successful model is used as a tool to support the construction company in assessing risk and evaluate their impact on the project’s profit for new projects. Keywords: risk management; risk assessment; Artificial Neural Network (ANN); Failure Mode and Effect Analysis (FMEA); construction project.
Article
While a growing body of literature focuses in detecting and analyzing the main reasons affecting project success, the use of these results in project portfolio management is still under investigation. Project critical success factors (CSFs) can serve as the fundamental criteria to prevent possible causes of failures with an effective project selection process, taking into account company strategic objectives, project manager's experience and the competitive environment.This research proposes an innovative methodology to help managers in assessing projects during the selection phase. The paper describes the design, development and testing stages of a decision support system to predict project performances. An artificial neural network (ANN), scalable to any set of CSFs, classifies the level of project's riskiness by extracting the experience of project managers from a set of past successful and unsuccessful projects. © 2015 Elsevier Ltd and Association for Project Management and the International Project Management Association.
Article
Extreme learning machine (ELM) is an emerging learning algorithm for the generalized single hidden layer feedforward neural networks, of which the hidden node parameters are randomly generated and the output weights are analytically computed. However, due to its shallow architecture, feature learning using ELM may not be effective for natural signals (e.g., images/videos), even with a large number of hidden nodes. To address this issue, in this paper, a new ELM-based hierarchical learning framework is proposed for multilayer perceptron. The proposed architecture is divided into two main components: 1) self-taught feature extraction followed by supervised feature classification and 2) they are bridged by random initialized hidden weights. The novelties of this paper are as follows: 1) unsupervised multilayer encoding is conducted for feature extraction, and an ELM-based sparse autoencoder is developed via ℓ₁ constraint. By doing so, it achieves more compact and meaningful feature representations than the original ELM; 2) by exploiting the advantages of ELM random feature mapping, the hierarchically encoded outputs are randomly projected before final decision making, which leads to a better generalization with faster learning speed; and 3) unlike the greedy layerwise training of deep learning (DL), the hidden layers of the proposed framework are trained in a forward manner. Once the previous layer is established, the weights of the current layer are fixed without fine-tuning. Therefore, it has much better learning efficiency than the DL. Extensive experiments on various widely used classification data sets show that the proposed algorithm achieves better and faster convergence than the existing state-of-the-art hierarchical learning methods. Furthermore, multiple applications in computer vision further confirm the generality and capability of the proposed learning scheme.