House Price Prediction Using Artificial Neural Network: A Comparative Study with Hedonic Price Model (in English)
Visit Limsombunchai and Sandhya Samarasinghe
The purpose of this paper is to empirically compare the predictive power of an artificial neural network model with the hedonic price model, to predict house prices in New Zealand. A sample of information on 200 houses in Christchurch, New Zealand, is randomly collected from Harcourt website. The information including house size, house age, house type, number of bedrooms, number of bathrooms, number of garages, facilities around the house and geographical location are considered. The empirical results presented in this paper support the potential of neural network for house price prediction, although some studies have commented on its black box nature and achieved different conclusions.
Keywords: House Price, Artificial Neural Network (ANN), Hedonic Model.
View Abstract 3126 Hit(s)
Download Fulltext 2490 Hit(s)