Using a machine learning approach for property market analysis
This report aims to predict the property market trend for Singapore and Hong Kong with Python and some packages including pandas and scikit-learn. A machine learning approach was applied to perform the predictions with three regression models selected. Raw data was collected from the region or count...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project |
| 語言: | English |
| 出版: |
2016
|
| 主題: | |
| 在線閱讀: | http://hdl.handle.net/10356/67393 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Nanyang Technological University |
| 語言: | English |
| 總結: | This report aims to predict the property market trend for Singapore and Hong Kong with Python and some packages including pandas and scikit-learn. A machine learning approach was applied to perform the predictions with three regression models selected. Raw data was collected from the region or country’s corresponding government website. Before performing the training and testing using regression models, the raw data went through data cleaning and preprocessing. In the end, the predictions with regression models were conducted. Linear regression fit the Hong Kong property market best, while the K-Nearest Neighbors with k equals 3 performs best in Singapore property market. However, the future trend for both markets cannot be obtained due to the lack of latest data for some macroeconomic factors. |
|---|