Housing price prediction using feedforward neural networks

• Main Author: Nadiah Ishak
• Other Authors: Wang Lipo
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/136839
• Institution: Nanyang Technological University

House price prediction is an essential tool in the housing market and basis for any decision making in order to maximize the benefits. This project uses an artificial neural network to develop a prediction model for housing prices in the Housing Development Board (HDB) resale market in Singapore. This study will also identify important determinants that will affect HDB resale prices. With the identified price determinants, the information will be feed into a neural network model for training, testing, and validation. The training models used for this study are the Decision Tree Model, Levenberg-Marquardt Algorithm and Stochastic Gradient Descent. Experiment results support the notion that an artificial neural network approach is a suitable tool as they are able to map out the interactions between different determinants used.