Housing price prediction using deep neural networks

• 主要作者: Yapary, Stephen
• 其他作者: Wang Lipo
• 格式: Final Year Project
• 語言: English
• 出版: Nanyang Technological University 2021
• 主題: Engineering::Electrical and electronic engineering
• 在線閱讀: https://hdl.handle.net/10356/149601
• 機構: Nanyang Technological University

Housing price prediction plays an essential role in helping both developers and customers to maximise their benefits. In this study, a comparison will be done between the performance of deep learning techniques and that of other machine learning algorithms in predicting the Housing Development Board Resale Price Index. The macroeconomic factors will be used as inputs for this study. There will be 3 different types of analysis: Fundamental, Technical and Combined analysis. Each type of analysis uses different input features to be fed into the machine learning models. The deep learning algorithms used in this project are the Long Short-Term Memory, Gated Recurrent Unit and Recurrent Neural Network. These deep learning algorithms will be compared with shallow Multi-Layer Perceptron, Support Vector Regressor and Gradient Boosting Regressor. The experiment result suggests that GRU in Combined Analysis is the best performing deep learning technique.