The development of a real estate economy is beneficial to urban stability. A method of real estate price prediction based on transport accessibility is proposed. The method adds bus accessibility and metro accessibility into the model, which has higher prediction accuracy than the traditional model. Firstly, bus accessibility and metro accessibility are calculated according to the space syntax theory. Then, four models, the traditional hedonic price model (HPM) with transport accessibility, the traditional hedonic price model without transport accessibility, the random forest (RF) model with transport accessibility, and the random forest model without transport accessibility, are introduced. Finally, the four models are compared and analyzed in terms of precision and importance of index contributions. Taking Xi ’an, China, as an example, the experimental results show that the transport accessibility calculated based on space syntax can accurately represent the transport convenience in an urban space structure. Furthermore, it has a great influence on the contribution of indexes in the model. With the introduction of bus accessibility and metro accessibility, the accuracy of the real estate price prediction model is greatly improved.

Based on the symmetrical public transportation network data of Xi’an, China obtained by geographic information system (GIS) technology in 2019, three urban public transportation indexes of walking accessibility, bus accessibility, and metro accessibility were established, and a real estate price prediction model was built by using several machine learning algorithms to predict and analysis the housing price in Xi’an, China. Firstly, the symmetrical road network data and real estate property data of Xi’an were collected and preprocessed, secondly, the spatial syntax theory and distance calculation method were applied to establish three indexes of traffic accessibility; finally, taking the house property data and the calculated traffic accessibility indexes as the characteristic index, the real estate price prediction model of Xi’an was constructed by using the random forest algorithm (RF), lightweight gradient lift algorithm (LGBM), and gradient lifting regression tree algorithm (GBDT). The prediction accuracy of the final model is 89.2% and the root-mean-square error is 1761.84. The results show that the accessibility of bus and metro to some extent represent the convenience of public transportation in different areas of urban space. The higher the accessibility index is, the more convenient the traffic is. The real estate price model has high prediction accuracy and can reflect the real situation of urban real estate price. The importance of the three accessibility features to the real estate price prediction model are nearly more than 20%, which indicates that the accessibility of urban public transportation has an important impact on the change of urban real estate price, and the development of urban public transportation plays an important role in the real estate economy.