Urban Residential Land Price Assessment Based on Transfer Learning

With the development of urbanization in China, the land economy accounts for more and more percentage in the gross domestic product (GDP) of China. Therefore, the accurate assessment of urban residential land price is of great interest for the governments. In the paper, we introduced the transfer learning to assess the urban residential land price, taking the Shenzhen city in China as a case. First, we collected housing price, land price data and points of interest (POI) data. The POI data was quantified as the influencing factors of two price data. Second, we used housing price data and influencing factors to train a high-accuracy model based on deep belief network (DBN). Third, we kept the DBN model unchanged, and then used three new models connected in order to better assess land price. The three models are back propagation (BP) neural network, support vector machine (SVM), and random forest (RF). Finally, we used land price data and influencing factors with three models to find the best one. The models were trained by the method of five-fold cross validation. Our results showed that all of three transfer learning models had good accuracy but the model with random forest was more suitable for the urban residential land price assessment. Therefore, our proposed method is an efficient approach to assess the urban residential land price with transfer learning.