Please use this identifier to cite or link to this item:
Title: Predicting private property prices using neural network
Authors: Ng, Brian Theng Koon.
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2011
Abstract: The objective of this academic study is to experiment and choose suitable economic indicators that are relevant to the Singapore economy to forecast the property price in Singapore. With this selected economic indicators, the study aim to establish the private property prices in Singapore with the help of Artificial Neural Networks (ANN). The predictive and generalization ability of the Artificial Neural Networks (ANN) will be used to explore private property price in Singapore. ANN is used in this forecast particularly due to its ability to handle non linear problem and give a good prediction. Similar experiments ANN have been carried out in Europe by [1] (E. Worzala et al, 1995) as regression methods which are used before by [2] (M.J. Bailey et al, 1963) in the 1960s are not a good enough predictor for the property price in a market (Singapore) that is much more volatile today compared to the past due to globalization . The historical data of these indicators which are found to be ideal will be used as input and will be used to train the Artificial Neural Networks (ANN), the trained Artificial Neural Networks (ANN) will be able to infer from the training based on the input indicators.This predictive ability of the trained ANN can be used by the government or economic planners in Singapore for further studies such as modeling the likely effects of new economic policies to adjust the property prices when there’s a need to intervene the property market. The housing index which is found on Bloomberg and SISV are used, the price is derived from resale transactions on the actual market. [3] (Bourassa et al., 2008) and [4] (N. García 2004) have shown that these data are usable for research in this area.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
1.97 MBMicrosoft WordView/Open

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.