The Deep Learning Approach to Property Valuation: An Application of a Multilayer Neural Net Model for Estimating House

The traditional approach to property valuation has been the use of a linear regression model, which has been criticized for assumption of a linear relationship between predictors and the house prices. We tried to overcome the limitation through the deep learning approach, that is, using a multi-hidden layer neural net model. Our finding is that the neural net model outperformed the traditional approach across all the four study areas. We interpreted that the outstanding performance of the neural net model could be attributed to the capability of non-linear modeling of predictors with the example being geographical coordinates. Another noticeable result is that the gap of the model performance between the neural net model and the traditional approach widened as the study area became more heterogeneous. The neural net model was proven to be able to perform more efficiently in the heterogeneous area where the traditional linear regression model suffered when predicting the house prices.