Residential property price time series forecasting with neural networks

Wilson, Ian D.; Paris, S. D.; Ware, Andrew; Jenkins, David H.

doi:10.1016/s0950-7051(01)00169-1

Cited by 59 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In developing an ANN model, the available data set is to be divided into two, i.e. for training and testing of the model (Wilson et al, 2002). The training data set is used to develop the model by determining the arc weights, while testing is the process of evaluating the predictive and generalization ability of the developed model (Lam et al, 2008).…”

Section: Model Specificationmentioning

confidence: 99%

Modelling property values in Nigeria using artificial neural network

Abidoye

Chan

2017

Journal of Property Research

View full text Add to dashboard Cite

Unreliable and inaccurate property valuation has been associated with techniques currently used in property valuation. A possible explanation for these findings may be due to the utilization of traditional valuation methods. In the current study, an artificial neural network (ANN) is applied to property valuation using the Lagos metropolis real estate market as a representative case. Property transactions data (11 property attributes and property value) were collected from registered real estate firms operating in Lagos, Nigeria. The result shows that the ANN model possesses a good predictive ability, implying that it is suitable and reliable for property valuation. The relative importance analysis conducted on the property attributes revealed that the number of servants' quarters is the most important attribute affecting property values. The findings suggest that the ANN model could be used as a tool by real estate stakeholders, especially, valuers and researchers for property valuation.

show abstract

Section: Model Specificationmentioning

confidence: 99%

Modelling property values in Nigeria using artificial neural network

Abidoye

Chan

2017

Journal of Property Research

View full text Add to dashboard Cite

show abstract

“…Therefore, accurate and reliable housing market forecasts are essential for all involved parties, including property buyers, owners, real estate brokers, investors, financial institutions, and decision-makers. The importance of housing market forecasts has been emphasized in numerous research studies (Billah, Hyndman, and Koehler 2005;Chatfield 2001;Chen et al 2014;Kishor and Marfatia 2017;Cañizares Martínez et al 2023;Wilson et al 2002).…”

Section: Discussionmentioning

confidence: 99%

Predicting Housing Price Trends in Poland: Online Social Engagement - Google Trends

Bełej

2023

Real Estate Management and Valuation

View full text Add to dashboard Cite

Various research methods can be used to collect housing market data and predict housing prices. The online search activity of Internet users is a novel and highly interesting measure of social behavior. In the present study, dwelling prices in Poland were analyzed based on aggregate data from seven Polish cities relative to the number of online searches for the keyword dwelling tracked by Google Trends, as well as several classical macroeconomic indicators. The analysis involved a vector autoregressive (VAR) model and the Granger causality test. The results of the study suggest that the volume of online searches returned by Google Trends is an effective predictor of housing price dynamics, and that unemployment and economic growth are important additional variables.

show abstract

“…Tay and Ho (1991), Do and Grudnitski (1992), Worzala et al (1995) and McGreal et al (1998) all examine the effectiveness of NN systems in property appraisal. Nguyen and Cripps (2001) compare the predictive accuracy of NNs against regression in forecasting housing values, and Wilson et al (2002) use NNs to forecast future trends within the UK housing market. Brooks and Tsolacos (2003) suggest that analysts should exploit the potential of NNs and assess more fully their forecast performance against more traditional models, and more recently, Ellis and Wilson (2005) examine the applicability of a neural network expert system in the construction of portfolios of Australian securitised property.…”

Section: Brief Overview Of Expert Systemsmentioning

confidence: 99%