A Pricing Model for Urban Rental Housing Based on Convolutional Neural Networks and Spatial Density: A Case Study of Wuhan, China

With the development of urbanization and the expansion of floating populations, rental housing has become an increasingly common living choice for many people, and housing rental prices have attracted great attention from individuals, enterprises and the government. The housing rental prices are principally estimated based on structural, locational and neighborhood variables, among which the relationships are complicated and can hardly be captured entirely by simple one-dimensional models; in addition, the influence of the geographic objects on the price may vary with the increase in their quantities. However, existing pricing models usually take those structural, locational and neighborhood variables as one-dimensional inputs into neural networks, and often neglect the aggregated effects of geographical objects, which may lead to fluctuating rental price estimations. Therefore, this paper proposes a rental housing price model based on the convolutional neural network (CNN) and the synthetic spatial density of points of interest (POIs). The CNN can efficiently extract the complex characteristics among the relevant variables of housing, and the two-dimensional locational and neighborhood variables, based on the synthetic spatial density, effectively reflect the aggregated effects of the urban facilities on rental housing prices, thereby improving the accuracy of the model. Taking Wuhan, China, as the study area, the proposed method achieves satisfactory and accurate rental price estimations (coefficient of determination (R2) = 0.9097, root mean square error (RMSE) = 3.5126) in comparison with other commonly used pricing models.

City Size and Permanent Settlement Intention: Evidence from Rural-Urban Migrants in China

The location choice and livelihoods of rural-urban migrants are critical to the sustainable development of cities. By using data from the China Migrants Dynamic Survey (CMDS) in 2017, this paper extant the Rosen–Roback’s model by adding factors of urban social network and air pollution to the function of the individual utility of migrants. Both the Probit Model and IV estimates imply evidence of an inverse U-shaped pattern of city size and migrants’ permanent settlement in urban China. This view proves that Chinese migrants like to settle permanently in large cities, but not mega-cities, such as Beijing and Shanghai. The internal mechanism is explained by the agglomeration economies and the crowing effect brought by city size. In mega-cities, the attractiveness of the city caused by wage premium cannot offset the combined repulsive force caused by the high housing price, bad urban social network, air pollution, and health deterioration. It is worth noting that air pollution has a significant negative impact on the settlement intention of migrants, such as health conditions and precipitation. Besides, there is heterogeneity among high-skilled migrants and low-skilled migrants in different city sizes. Our findings enhance the understanding of “Escape from megacities” in China and have implications for the reform of the housing security system and the exploration of the urbanization path.

Gulf property damage, housing price trends and US bankruptcy filings

Purpose This paper aims to examine potential causes of bankruptcy as they relate to hurricane damage. Investigate whether hurricanes result in personal bankruptcy filings due to real property damages. Strengthen existing descriptive results by using fully modified ordinary least squares (FMOLS). Design/methodology/approach Lagged FMOLS model is used with data from states that suffered hurricane damage between 2000 through 2020. FMOLS controls for various financial distresses that can cause bankruptcy filings. Findings Bankruptcy is usually filed for within one year of a hurricane. Changes in house prices and hurricane severity were significant indicators of bankruptcy filings. However, the divorce rate, commonly thought of as a primary reason for bankruptcy, is insignificant. Research limitations/implications Data was available on a state level for the independent variables. Hurricane damage needed to be financially significant enough for inland flooding to be measurable and influential. Practical implications Establishes that financial distress comes from several sources, not just home damage. Financial distress is highly correlated with whether a home was insured. Divorce does not cause bankruptcy filings. Social implications Federal flood insurance programs should be reexamined. Having a broader all-risk homeowner policy could reduce the number of households that file for bankruptcy after a hurricane. Originality/value Existing research uses descriptive statistics and obtains mixed findings regarding the association between hurricane damage and bankruptcy filings. The FMOLS approach provides clarity about this association.