Abstract
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.
Highlights
With the rise of China’s house prices, the issue of house price has gradually become the focus of the government, consumers, investors, and academic researchers [1]
3.5 determines the best housing price prediction model, and proves the superiority of calculating traffic accessibility through spatial syntax, in order to better explore the impact of traffic on housing price, the content of this section will analyze the common characteristics of the model based on the proportion of the characteristics of the four types of machine learning algorithms previously determined
Three characteristic indexes of walking accessibility, bus accessibility and metro accessibility are calculated, which are introduced into the influencing factors of real estate price, and four machine algorithms are used to predict the real estate price in the whole city, good prediction results have been obtained
Summary
With the rise of China’s house prices, the issue of house price has gradually become the focus of the government, consumers, investors, and academic researchers [1]. When people conduct real estate transactions, most of them are based on field investigation and qualitative analysis, which is limited by the factors of both parties, there is no evaluation standard that can reasonably price the house itself, which will lead to unfair transaction to a certain extent [2]. How to quantitatively evaluate the price of the house and determine the main factors affecting the price of the house has become a big problem [3]. The development of public transport in the city can, to a certain extent, improve the regional economic vitality and promote the development of the real estate economy [4]. Under the background of big data, how to use massive data to reasonably
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
