Providing adequate public rental housing (PRH) of a decent quality at a desirable location is a major challenge in many cities. Often, a prominent opponent of PRH development is its host community, driven by a belief that PRH depreciates nearby property values. While this is a persistent issue in many cities around the world, this study proposed a new approach to assessing the impact of PRH on nearby property value. This study utilized a machine learning technique called long short-term memory (LSTM) to construct a set of housing price prediction models based on 547,740 apartment transaction records from the city of Busan, South Korea. A set of apartment characteristics and proximity measures to PRH were included in the modeling process. Four geographic boundaries were analyzed: The entire region of Busan, all neighborhoods of PRH, the neighborhoods of PRH in the “favorable,” and the “less favorable” local housing market. The study produced accurate and reliable price predictions, which indicated that the proximity to PRH has a meaningful impact on nearby housing prices both at the city and the neighborhood level. The approach taken by the study can facilitate improved decision making for future PRH policies and programs.

The increasing energy burden on vulnerable households is critical in modern cities, it is crucial to understand how cities can characterize energy vulnerability and its relationship with the environment. This study modeled relationships between energy consumption and built environmental factors to compare determinants in average and energy-vulnerable households. While the conventional approach of identifying energy vulnerability often relies on household income, this study suggested a new approach by considering the energy-vulnerable group as a low-income class with high energy expenditure. A traditional regression model (semi-log regression) and advanced machine learning algorithm (ensemble gradient boosting, XGboost) were employed to maximize the performance of the modeling processes. The results indicated that the overall modeling performance was superior with regard to the machine learning algorithm, producing the r-squared value of 0.92 for the energy-vulnerable households, compared to the 0.34 of the semi-log regression model. While the direction of the association of the determinants was similar in the average and energy-vulnerable households, the level of association exhibited a clear difference, especially for the effect of income (comparing 0.30 to 0.03) and housing type (comparing -0.45 to -0.63). The study identified several implications regarding urban energy management and policy based on the findings.

The safety of senior pedestrians is a major challenge in cities, particularly in a rapidly aging society. This study takes place in Seoul, South Korea, where pedestrian safety in highly urban environments poses a major threat. Using several big databases, the study investigated 142 frequent collision areas where 583 pedestrian-vehicle collisions involving seniors were reported in 2017. Using Poisson and negative binomial regression, we modeled the relationship between collisions and three sets of area-specific environmental characteristics: land-use; transportation and pedestrian infrastructures; and population characteristics. Two different scales of walking environment of senior citizens were investigated: the frequent collision areas (200-meter radius), and their pedestrian sheds (1-kilometer radius). The study further dissectedcommercial areas and roadways into types of destinations and roadway classifications, and found that the neighborhoods with a higher number of medical institutes and a denser network of minor roads were associated with higher risk of collisions. The study found that senior pedestrians were more vulnerable in low-income neighborhoods, especially in the areas with larger resident and floating population of seniors. The findings from the study provided some meaningful information on the risk of collision, and policy implications to improve the safety of senior pedestrians.