Search results

1 – 10 of 850
Per page
102050
Citations:
Loading...
Access Restricted. View access options
Article
Publication date: 30 March 2020

Joseph Awoamim Yacim and Douw Gert Brand Boshoff

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…

308

Abstract

Purpose

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.

Design/methodology/approach

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.

Findings

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.

Originality/value

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.

Details

Property Management, vol. 38 no. 2
Type: Research Article
ISSN: 0263-7472

Keywords

Access Restricted. View access options
Book part
Publication date: 10 June 2016

William Terrill, Eugene A. Paoline and Jacinta M. Gau

This chapter seeks to illuminate the interconnectedness of procedural justice, use of force, and occupational culture in relation to police legitimacy.

Abstract

Purpose

This chapter seeks to illuminate the interconnectedness of procedural justice, use of force, and occupational culture in relation to police legitimacy.

Methodology/approach

The authors review the existing literature and offer an integrated methodological approach that would better assist researchers in their quest to enhance police legitimacy.

Findings

Using a systematic design that assesses police legitimacy from a variety of sources has the potential to help answer critical questions with regard to improving police practice.

Originality/value

This is a novel study approach, which has yet to be implemented but which may offer great insight with respect to improving police legitimacy.

Details

The Politics of Policing: Between Force and Legitimacy
Type: Book
ISBN: 978-1-78635-030-5

Keywords

Access Restricted. View access options
Article
Publication date: 14 February 2018

Joseph Awoamim Yacim and Douw Gert Brand Boshoff

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…

251

Abstract

Purpose

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.

Design/methodology/approach

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.

Findings

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.

Research limitations/implications

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.

Originality/value

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.

Details

International Journal of Housing Markets and Analysis, vol. 11 no. 2
Type: Research Article
ISSN: 1753-8270

Keywords

Access Restricted. View access options
Article
Publication date: 10 October 2023

Visar Hoxha

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

164

Abstract

Purpose

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

Design/methodology/approach

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.

Findings

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.

Practical implications

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.

Originality/value

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.

Access Restricted. View access options
Article
Publication date: 16 November 2018

Michael J. McCord, Sean MacIntyre, Paul Bidanset, Daniel Lo and Peadar Davis

Air quality, noise and proximity to urban infrastructure can arguably have an important impact on the quality of life. Environmental quality (the price of good health) has become…

689

Abstract

Purpose

Air quality, noise and proximity to urban infrastructure can arguably have an important impact on the quality of life. Environmental quality (the price of good health) has become a central tenet for consumer choice in urban locales when deciding on a residential neighbourhood. Unlike the market for most tangible goods, the market for environmental quality does not yield an observable per unit price effect. As no explicit price exists for a unit of environmental quality, this paper aims to use the housing market to derive its implicit price and test whether these constituent elements of health and well-being are indeed capitalised into property prices and thus implicitly priced in the market place.

Design/methodology/approach

A considerable number of studies have used hedonic pricing models by incorporating spatial effects to assess the impact of air quality, noise and proximity to noise pollutants on property market pricing. This study presents a spatial analysis of air quality and noise pollution and their association with house prices, using 2,501 sale transactions for the period 2013. To assess the impact of the pollutants, three different spatial modelling approaches are used, namely, ordinary least squares using spatial dummies, a geographically weighted regression (GWR) and a spatial lag model (SLM).

Findings

The findings suggest that air quality pollutants have an adverse impact on house prices, which fluctuate across the urban area. The analysis suggests that the noise level does matter, although this varies significantly over the urban setting and varies by source.

Originality/value

Air quality and environmental noise pollution are important concerns for health and well-being. Noise impact seems to depend not only on the noise intensity to which dwellings are exposed but also on the nature of the noise source. This may suggest the presence of other externalities that arouse social aversion. This research presents an original study utilising advanced spatial modelling approaches. The research has value in further understanding the market impact of environmental factors and in providing findings to support local air zone management strategies, noise abatement and management strategies and is of value to the wider urban planning and public health disciplines.

Details

Journal of European Real Estate Research, vol. 11 no. 3
Type: Research Article
ISSN: 1753-9269

Keywords

Access Restricted. View access options
Article
Publication date: 1 April 1991

J.N. Berry, W.J. McCluskey, W.S. McGreal and T. Beamish

Looks at mechanisms to encourage the growth of the small industrialsector in Northern Ireland. Evaluates the respective ideas of enterpriseagencies and the private developers�…

266

Abstract

Looks at mechanisms to encourage the growth of the small industrial sector in Northern Ireland. Evaluates the respective ideas of enterprise agencies and the private developers′ scheme, together with opinions of users (tenants) and developers. Concludes that slow rental growth means that grant assistance is necessary to ensure a moderate level of return to the developer.

Details

Journal of Property Finance, vol. 2 no. 1
Type: Research Article
ISSN: 0958-868X

Keywords

Access Restricted. View access options
Article
Publication date: 21 August 2007

William J. McCluskey and Richard A. Borst

The purpose of this research is to explore from a mass appraisal perspective how the effects of location are reflected within valuation models. The paper sets out to detail the…

1660

Abstract

Purpose

The purpose of this research is to explore from a mass appraisal perspective how the effects of location are reflected within valuation models. The paper sets out to detail the various techniques and the efficacy of their application.

Design/methodology/approach

The approach adopted is analytical and based upon the development of locational attributes. An extensive literature base is synthesized with methods being evaluated in their application to mass appraisal.

Findings

This research has identified that the three main groups interested in residential property valuation, namely, academia, industry and commerce have to a certain extent been unfamiliar with the research developments occurring in the other groups. The impact of this is important, given the need for integration and collaboration in terms of future model development.

Research limitations/implications

The research underpinning this paper will provide a solid basis for further research into this area. The importance of measuring the effect that location has on value is of major significance in the determination of objective estimates of property value.

Practical implications

Those within the assessment community could be described as pragmatists working in a situation that requires feasible and suitable solutions to the problem of measuring location value. It is our contention that the third generation techniques of spatially varying parameter models and spatial autocorrelation models will require greater industry verification before their use becomes more widely accepted.

Originality/value

This paper provides a detailed analysis of methodologies used to reflect the value of location over the last 50 years. The debate is taken forward by describing what will be the contribution to the development of the next generation of location‐specific modeling techniques.

Details

Property Management, vol. 25 no. 4
Type: Research Article
ISSN: 0263-7472

Keywords

Access Restricted. View access options
Article
Publication date: 5 August 2019

Olalekan Shamsideen Oshodi, Wellington Didibhuku Thwala, Tawakalitu Bisola Odubiyi, Rotimi Boluwatife Abidoye and Clinton Ohis Aigbavboa

Estimation of the rental price of a residential property is important to real estate investors, financial institutions, buyers and the government. These estimates provide…

482

Abstract

Purpose

Estimation of the rental price of a residential property is important to real estate investors, financial institutions, buyers and the government. These estimates provide information for assessing the economic viability and the tax accruable, respectively. The purpose of this study is to develop a neural network model for estimating the rental prices of residential properties in Cape Town, South Africa.

Design/methodology/approach

Data were collected on 14 property attributes and the rental prices were collected from relevant sources. The neural network algorithm was used for model estimation and validation. The data relating to 286 residential properties were collected in 2018.

Findings

The results show that the predictive accuracy of the developed neural network model is 78.95 per cent. Based on the sensitivity analysis of the model, it was revealed that balcony and floor area have the most significant impact on the rental price of residential properties. However, parking type and swimming pool had the least impact on rental price. Also, the availability of garden and proximity of police station had a low impact on rental price when compared to balcony.

Practical implications

In the light of these results, the developed neural network model could be used to estimate rental price for taxation. Also, the significant variables identified need to be included in the designs of new residential homes and this would ensure optimal returns to the investors.

Originality/value

A number of studies have shown that crime influences the value of residential properties. However, to the best of the authors’ knowledge, there is limited research investigating this relationship within the South African context.

Details

Journal of Financial Management of Property and Construction , vol. 24 no. 2
Type: Research Article
ISSN: 1366-4387

Keywords

Access Restricted. View access options
Article
Publication date: 22 June 2012

Peadar Davis, William McCluskey, Terry V. Grissom and Michael McCord

This paper seeks to examine the potential for simplified market value and non market value based banded approaches to be utilised for residential property tax purposes. The broad…

1032

Abstract

Purpose

This paper seeks to examine the potential for simplified market value and non market value based banded approaches to be utilised for residential property tax purposes. The broad aim is to ascertain whether relatively low complexity approaches to establishing a property tax base can perform adequately in comparison to established best practice – in essence whether there is evidence of equifinality (equivalent performance from approaches of substantially different complexity) between simpler and more complex approaches.

Design/methodology/approach

The research comprises empirical analysis of a database of property sales and property attribute data drawn from a UK District Council area. Several simplified methods are used to create different tax base scenarios and the outflowing tax incidence is compared with that of using a complex, industry standard market value approach. The methods of comparison are regression and spline regression based models testing for tax inequity, drawn from the literature. The approach here differs from previous work in that it occurs at the actual tax bill level allowing the comparison of value, non‐value and banded approaches.

Findings

The findings of the research indicate that simplified approaches to establishing a property tax base can perform in a broadly similar fashion to more complex systems currently practiced in developed economies and therefore evidence of equifinality exists.

Practical implications

The research provides useful tools to property tax policy makers and practitioners in developing and transitional economies in furthering their aspirations of embedding robust property taxes for the furtherance of socio‐economic and political development and the general wellbeing of society and they are of value to property tax policy makers and to academics in the field.

Originality/value

The paper provides evidence of the efficacy of simplified and banded approaches as an option for jurisdictions in developing and transitional economic circumstances or elsewhere in circumstances which mitigate against full scale appraisal of the property tax base to discrete market values. The approaches and techniques pioneered open up opportunities to carry out a range of new comparative analysis of tax base options.

Access Restricted. View access options
Article
Publication date: 1 September 2005

John D. McCluskey and William Terrill

This paper seeks to examine a variety of measures of complaints and their relationship to police officers' use of coercion in encounters with suspects.

1674

Abstract

Purpose

This paper seeks to examine a variety of measures of complaints and their relationship to police officers' use of coercion in encounters with suspects.

Design/methodology/approach

Data from the Project on Policing Neighborhoods, involving the systematic social observation of police, were combined with complaint data from the St Petersburg Police Department to examine the influence of complaints on use of coercion in everyday encounters. Hierarchical models, which included theoretically relevant control variables, were used to test multiple measures of departmental and citizen complaints as predictors of officers' use of coercion.

Findings

The analyses indicate that, net of other important predictors, officer complaint rate for force and verbal discourtesy is associated with higher levels of coercion in encounters with suspects. The analyses also indicate that officers' verbal discourtesy complaint rate is associated with higher levels of coercion, but complaint rates for physical force are not related to higher levels of coercion.

Research limitations/implications

The current results do not necessarily generalize to all police departments, since the department, at that time, was a leader in community policing.

Practical implications

The influence of complaints for force and discourtesy on coercion suggests that police departments could benefit from greater attention toward officers who generate complaints for discourtesy from the public.

Originality/value

This paper examines the utility of official complaint data as a determinant of officers' coercive behavior in encounters with suspects. The research would be of interest to police executives concerned with creating “early warning systems” as well as police scholars concerned with the determinants of officer coercion.

Details

Policing: An International Journal of Police Strategies & Management, vol. 28 no. 3
Type: Research Article
ISSN: 1363-951X

Keywords

1 – 10 of 850
Per page
102050