Search results

Booms and bubbles are inevitable in the real estate industry. Loss of profits, bankruptcy and economic slowdown are indicators of the adverse effects of fluctuations in property prices. Models providing a reliable forecast of property prices are vital for mitigating the effects of these variations. Hence, this study aims to investigate the use of artificial intelligence (AI) for the prediction of property price index (PPI).

Information on the variables that influence property prices was collected from reliable sources in Hong Kong. The data were fitted to an autoregressive integrated moving average (ARIMA), artificial neural network (ANN) and support vector machine (SVM) models. Subsequently, the developed models were used to generate out-of-sample predictions of property prices.

Based on the prediction evaluation metrics, it was revealed that the ANN model outperformed the SVM and ARIMA models. It was also found that interest rate, unemployment rate and household size are the three most significant variables that could influence the prices of properties in the study area.

The findings of this study provide useful information to stakeholders for policy formation and strategies for real estate investments and sustained growth of the property market.

The application of the SVM model in the prediction of PPI in the study area is lacking. This study evaluates its performance in relation to ANN and ARIMA.

The purpose of the study is to examine the efficiency of linear, nonlinear and artificial neural networks (ANNs), in predicting property prices.

The present study uses a dataset of 1,468 real estate transactions from 2020 to 2022, obtained from the Department of Property Taxes of Republic of Kosovo. Beginning with a fundamental linear regression model, the study tackles the question of overlooked nonlinearity, employing a similar strategy like Peterson and Flanagan (2009) and McCluskey et al. (2012), whereby ANN's predictions are incorporated as an additional regressor within the ordinary least squares (OLS) model.

The research findings underscore the superior fit of semi-log and double-log models over the OLS model, while the ANN model shows moderate performance, contrary to the conventional conviction of ANN's superior predictive power. This is notably divergent from the prevailing belief about ANN's superior predictive power, shedding light on the potential overestimation of ANN's efficacy.

The study accentuates the importance of embracing diverse models in property price prediction, debunking the notion of the ubiquitous applicability of ANN models. The research outcomes carry substantial ramifications for both scholars and professionals engaged in property valuation.

Distinctively, this research pioneers the comparative analysis of diverse models, including ANN, in the setting of a developing country's capital, hence providing a fresh perspective to their effectiveness in property price prediction.

Describes an attempt to predict the value of private properties in the Stafford area from information typically available about the properties’ physical characteristics and location. Discusses the factors influencing property values, including the complicating effect of location, and attempts to build a predictive model using the statistical technique of multiple regression analysis, based on physical characteristics only and ignoring the effect of location. Makes further refinements to the predictions produced by incorporating an additional location effect modelled by means of surface‐fitting techniques within a geographical information system. The results, many of which are presented graphically, are shown to be a significant improvement on the location‐blind model. Offers suggested directions for further research and development of the technique.

An appraisal by an accredited appraiser is often necessary before a proposed development can receive a commitment for financing from a financial institution. Such pre‐construction appraisals are often more difficult to complete than those where the subject property is already developed and accessible for inspection. In this article we are performing a valuation of a proposed townhouse complex prior to its construction. Hedonic estimation is used to estimate the market value of the proposed development. The estimated value of the complex as a whole, and of the individual units, is compared to the prices obtained as the townhouses were built and sold. Insights with respect to the feasibility of the approach for the estimation of the gross retail value of proposed developments are discussed.

The paper introduced the use of a hybrid system of neural networks support vector machines (NNSVMs) consisting of artificial neural networks (ANNs) and support vector machines (SVMs) to price single-family properties.

The mechanism of the hybrid system is such that its output is given by the SVMs which utilise the results of the ANNs as their input. The results are compared to other property pricing modelling techniques including the standalone ANNs, SVMs, geographically weighted regression (GWR), spatial error model (SEM), spatial lag model (SLM) and the ordinary least squares (OLS). The techniques were applied to a dataset of 3,225 properties sold during the period, January 2012 to May 2014 in Cape Town, South Africa.

The results demonstrate that the hybrid system performed better than ANNs, SVMs and the OLS. However, in comparison to the spatial models (GWR, SEM and SLM) the hybrid system performed abysmally under with SEM favoured as the best pricing technique.

The findings extend the debate in the body of knowledge that the results of the OLS can significantly be improved through the use of spatial models that correct bias estimates and vary prices across the different property locations. Additionally, utilising the result of the hybrid system is thus affected by the black-box nature of the ANNs and SVMs limiting its use to purposes of checks on estimates predicted by the regression-based models.

It is important to forecast local trading volumes as well as global trading volumes because the real estate market is always characterized as a localized market. The house trading volume at the local level is forecast through appropriate models to enhance the predictive accuracy.

Four representative housing submarkets in South Korea are selected, and their trading volumes are forecast. A well-established time-series model and a deep learning algorithm are employed: the autoregressive integrated moving average (ARIMA) model and the recurrent neural network (RNN), respectively. The trading volumes in adjacent areas are utilized as covariates, and an ensemble prediction is applied additionally to improve the model performance.

The results indicate no significant difference in prediction performance between the ARIMA model and the RNN, which can be attributed to the insufficient amount of data used. It is discovered that the spillover effects of trading volumes across the study areas can be exploited to improve the predictive accuracy, and that the diversity of the predicted values from the candidate models can be used to increase the forecasting accuracy further.

Whereas property prices have been investigated extensively, the discussion on forecasting trading activity of properties is limited in the literature. The results of this study are expected to promote more interest in adopting a local perspective and using a diversity of predicted values when forecasting house trading volumes.

The purpose of this study is to compare the predictive performance of the hedonic multivariate regression model with the probabilistic neural network (PNN)-based general regression neural network (GRNN) model of housing prices in “Pune-India.”

Data on 211 properties across “Pune city-India” is collected. The price per square feet is considered as a dependent variable whereas distances from important landmarks such as railway station, fort, university, airport, hospital, temple, parks, solid waste site and stadium are considered as independent variables along with a dummy for amenities. The data is analyzed using a hedonic type multivariate regression model and GRNN. The GRNN divides the entire data set into two sets, namely, training set and testing set and establishes a functional relationship between the dependent and target variables based on the probability density function of the training data (Alomair and Garrouch, 2016).

While comparing the performance of the hedonic multivariate regression model and PNN-based GRNN, the study finds that the output variable (i.e. price) has been accurately predicted by the GRNN model. All the 42 observations of the testing set are correctly classified giving an accuracy rate of 100%. According to Cortez (2015), a value close to 100% indicates that the model can correctly classify the test data set. Further, the root mean square error (RMSE) value for the final testing for the GRNN model is 0.089 compared to 0.146 for the hedonic multivariate regression model. A lesser value of RMSE indicates that the model contains smaller errors and is a better fit. Therefore, it is concluded that GRNN is a better model to predict the housing price functions. The distance from the solid waste site has the highest degree of variable senstivity impact on the housing prices (22.59%) followed by distance from university (17.78%) and fort (17.73%).

The study being a “case” is restricted to a particular geographic location hence, the findings of the study cannot be generalized. Further, as the objective of the study is restricted to just to compare the predictive performance of two models, it is felt appropriate to restrict the scope of work by focusing only on “location specific hedonic factors,” as determinants of housing prices.

The study opens up a new dimension for scholars working in the field of housing prices/valuation. Authors do not rule out the use of traditional statistical techniques such as ordinary least square regression but strongly recommend that it is high time scholars use advanced statistical methods to develop the domain. The application of GRNN, artificial intelligence or other techniques such as auto regressive integrated moving average and vector auto regression modeling helps analyze the data in a much more sophisticated manner and help come up with more robust and conclusive evidence.

To the best of the author’s knowledge, it is the first case study that compares the predictive performance of the hedonic multivariate regression model with the PNN-based GRNN model for housing prices in India.

There are a plethora of putative influencing variables available in the literature for modelling real estate prices using AI. Their choice tends to differ from one researcher to the other, consequently leading to subjectivity in the selection process. Thus, there is a need to seek the viewpoint of practitioners on the applicability and level of significance of these academically established variables.

Using the Delphi technique, this study collated and structured the 35 underlying micro- and macroeconomic parameters derived from literature and eight variables suggested by 11 selected real estate experts. The experts ranked these variables in order of influence using a seven-point Likert scale with a reasonable consensus during the fourth round (Kendall's W = 0.7418).

The study discovered that 16 variables are very influential with seven being extremely influential. These extremely influential variables include flexibility, adaptability of design, accessibility to the building, the size of office spaces, quality of construction, state of repairs, expected capital growth and proximity to volatile areas.

The results of this study improve the quality of data available to valuers towards a fortified price prediction for investors, and thereby, restoring the valuers' credibility and integrity.

The “volatility level of an area”, which was revealed as a distinct factor in the survey is used to add to current knowledge concerning office price. Hence, this study offers real estate practitioners and researchers valuable knowledge on the critical variables that must be considered in AI-based price modelling.

In this study the authors aim to outline new ways of information extraction for automated valuation models, which in turn would help to increase transparency in valuation procedures and thus contribute to more reliable statements about the value of real estate.

The authors hypothesize that empirical error in the interpretation and qualitative assessment of visual content can be minimized by collating the assessments of multiple individuals and through use of repeated trials. Motivated by this problem, the authors developed an experimental approach for semi-automatic extraction of qualitative real estate metadata based on Comparative Judgments and Deep Learning. The authors evaluate the feasibility of our approach with the help of Hedonic Models.

The results show that the collated assessments of qualitative features of interior images show a notable effect on the price models and thus over potential for further research within this paradigm.

To the best of the authors’ knowledge, this is the first approach that combines and collates the subjective ratings of visual features and deep learning for real estate use cases.

The aim of this paper is to investigate the comparative performance of an artificial neural network (ANN) and several multiple regression techniques in terms of their predictive accuracy and capability of being used within the mass appraisal industry.

The methodology first tested that the data set had neglected non‐linearity which suggested that a non‐linear modelling technique should be applied. Given the capability of ANNs to model non‐linear data, this technique was used along with an OLS regression model (baseline model) and two non‐linear multiple regression techniques. In addition, the models were evaluated in terms of predictive accuracy and their capability of use within the mass appraisal environment.

Previous studies which have compared the predictive performance of an ANN model against multiple regression techniques are inconclusive. Having superior predictive capability is important but equally important is whether the technique can be successfully employed for the mass appraisal of residential property. This research found that a non‐linear regression model had higher predictive accuracy than the ANN. Also the output of the ANN was not sufficiently transparent to provide an unambiguous appraisal model upon which predicted values could be defended against objections.

The research provides an informative view as to the efficacy of ANN methodology within the real estate field. A number of issues have been raised on the applicability of ANN models within the mass appraisal environment.

This work demonstrates that ANNs whilst useful as a predictive tool have a limited practical role for the assessment of residential property values for property tax purposes.

The work has taken forward the debate on the usefulness of ANN techniques within the mass appraisal environment.