Search results

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.

Several studies have examined the impact of market fundamentals on house prices. However, the effect of economic sectors on housing prices is limited despite the existence of two-speed economies in some countries, such as South Africa. Therefore, this study aims to examine the impact of mining activities on house prices. This intends to understand the direction of house price spreads and their duration so policymakers can provide remediation to the housing market disturbance swiftly.

This study investigated the effect of mining activities on house prices in South Africa, using quarterly data from 2000Q1 to 2019Q1 and deploying an auto-regressive distributed lag model.

In the short run, we found that changes in mining activities, as measured by the contribution of this sector to gross domestic product, impact the housing price of mining towns directly after the first quarter and after the second quarter in the non-mining cities. Second, we found that inflationary pressure is instantaneous and impacts house prices in mining towns only in the short run but not in the long run, while increasing housing supply will help cushion house prices in both submarkets. This study extended the analysis by examining a possible spillover in house prices between mining and non-mining towns. This study found evidence of spillover in housing prices from mining towns to non-mining towns without any reciprocity. In the long run, a mortgage lending rate and housing supply are significant, while all the explanatory variables in the non-mining towns are insignificant.

These results reveal that enhanced mining activities will increase housing prices in mining towns after the first quarter, which is expected to spill over to non-mining towns in the next quarter. These findings will inform housing policymakers about stabilising the housing market in mining and non-mining towns. To the best of the authors’ knowledge, this study is the first to measure the contribution of mining to house price spillover.

The paper aims to investigate the application of particle swarm optimisation and back propagation in weights optimisation and training of artificial neural networks within the mass appraisal industry and to compare the performance with standalone back propagation, genetic algorithm with back propagation and regression models.

The study utilised linear regression modelling before the semi-log and log-log models with a sample of 3,242 single-family dwellings. This was followed by the hybrid systems in the selection of optimal attribute weights and training of the artificial neural networks. Also, the standalone back propagation algorithm was used for the network training, and finally, the performance of each model was evaluated using accuracy test statistics.

The study found that combining particle swarm optimisation with back propagation in global and local search for attribute weights enhances the predictive accuracy of artificial neural networks. This also enhances transparency of the process, because it shows relative importance of attributes.

A robust assessment of the models’ predictive accuracy was inhibited by fewer accuracy test statistics found in the software. The research demonstrates the efficacy of combining two models in the assessment of property values.

This work demonstrated the practicability of combining particle swarm optimisation with back propagation algorithms in finding optimal weights and training of the artificial neural networks within the mass appraisal environment.

This study aims to examine the statutory provisions as it concerns the practice of valuation for compensation of expropriated communal properties in Zimbabwe. The primary motivation was to have informed policies that would regulate the practice of landed property assessments for compensation purposes and further contributes to existing compensation debates.

A multiple case study approach was adopted, in which property valuation projects for Chiyadzwa and Tokwe-Mukosi, provinces were selected. These two projects were chosen because they are the most recent property valuation for compensation on expropriated communal properties. Content analysis was used to analyse the statutory provisions guiding property valuation and compensation rates adopted and used during the Chiyadzwa and Tokwe Mukosi valuation projects.

The study found an absence of statutory guidelines on the choice of valuation methodologies, leading to inconsistencies in compensation estimates for the communal properties.

The study dwells on data from the previous assessment of communal properties that triggered discontentment amongst the people to build a framework for future valuations of communal properties.

This study reviewed the existing expropriation and compensation laws and built a comprehensive guiding framework for property valuers to choose appropriate valuation methodologies and procedures for the assessment of expropriated communal properties in Zimbabwe.

The main motivation for this study is to find a lasting solution to frequent court cases and clashes between the government of Zimbabwe and the displaced people.

No study unravels the detailed property valuation processes used in determining the amount of payment for the expropriated communal properties in Zimbabwe. This study built a framework that will serve as a guide to the property valuers in the assessment of compensation for communal properties.

The challenge of accessibility to adequate housing in several countries by a large percentage of citizens has given rise to different housing programs designed to facilitate access to affordable housing. In South Africa, the National Housing Finance Corporation (NHFC) was created to provides housing loans to low- and middle-income earners. Thus, the purpose of this study was to evaluate the implication of the macroeconomic risk elements on the performance of the NHFC incremental housing finance.

This study used a mixed-method approach to examine the time-series data of the NHFC over 17 years (2003–2020), relative to selected macroeconomic indicators. Additionally, this study analysed primary data from a 2022 survey of NHFC Executives.

This study found that incremental housing finance addresses a housing affordability gap, caters to disadvantaged groups, adapts to changing macroeconomic conditions and can mitigate default risk. It also finds that the performance of the NHFC’s incremental housing finance is premised on the behaviour of the macroeconomic elements that drive its strategy in South Africa.

Unlike previous works on housing finance, this case study of the NHFC considers the implication of macroeconomic trends when disbursing incremental housing finance to low- and middle-level income earners as a risk mitigation measure for the South African market. Its mixed method use of quantitative and qualitative data also allows a robust insight into trends that drive investment in incremental housing finance in South Africa.

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.