Modeling property markets using neural network
The property market is a safe and appreciating asset class in many cities, hence represents an excellent investment opportunity for investors. With vibrant yet volatile activities in the property sector, it is crucial for investors to time their entry and exit into the property market for higher rat...
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project (FYP) |
Language: | English |
Published: |
2011
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/45657 |
_version_ | 1811685155828400128 |
---|---|
author | Chew, Kelvin Yuan Sheng. |
author2 | Quah Tong Seng |
author_facet | Quah Tong Seng Chew, Kelvin Yuan Sheng. |
author_sort | Chew, Kelvin Yuan Sheng. |
collection | NTU |
description | The property market is a safe and appreciating asset class in many cities, hence represents an excellent investment opportunity for investors. With vibrant yet volatile activities in the property sector, it is crucial for investors to time their entry and exit into the property market for higher rate of returns. The report investigated the effectiveness of a number of neural network architectures in predicting property housing prices. The most accurate architecture found was the general regression network with the ability to predict public housing prices with a small error of less than 4%, hence revealing the effectiveness of neural network in predicting housing prices. |
first_indexed | 2024-10-01T04:40:02Z |
format | Final Year Project (FYP) |
id | ntu-10356/45657 |
institution | Nanyang Technological University |
language | English |
last_indexed | 2024-10-01T04:40:02Z |
publishDate | 2011 |
record_format | dspace |
spelling | ntu-10356/456572023-07-07T16:17:26Z Modeling property markets using neural network Chew, Kelvin Yuan Sheng. Quah Tong Seng School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation The property market is a safe and appreciating asset class in many cities, hence represents an excellent investment opportunity for investors. With vibrant yet volatile activities in the property sector, it is crucial for investors to time their entry and exit into the property market for higher rate of returns. The report investigated the effectiveness of a number of neural network architectures in predicting property housing prices. The most accurate architecture found was the general regression network with the ability to predict public housing prices with a small error of less than 4%, hence revealing the effectiveness of neural network in predicting housing prices. Bachelor of Engineering 2011-06-16T01:19:44Z 2011-06-16T01:19:44Z 2011 2011 Final Year Project (FYP) http://hdl.handle.net/10356/45657 en Nanyang Technological University 45 p. application/pdf |
spellingShingle | DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation Chew, Kelvin Yuan Sheng. Modeling property markets using neural network |
title | Modeling property markets using neural network |
title_full | Modeling property markets using neural network |
title_fullStr | Modeling property markets using neural network |
title_full_unstemmed | Modeling property markets using neural network |
title_short | Modeling property markets using neural network |
title_sort | modeling property markets using neural network |
topic | DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation |
url | http://hdl.handle.net/10356/45657 |
work_keys_str_mv | AT chewkelvinyuansheng modelingpropertymarketsusingneuralnetwork |