Spatiotemporal Analysis of Chicago Ridesharing Demand using Modified Spatial Error Model

Ridesharing has transformed urban transportation by altering the mobility patterns in major cities. To understand the complex interplay of demographic, socioeconomic, and infrastructural factors, it is necessary to employ a spatial and temporal analytical approach. This study utilized a modified version of the Spatial Error Model (SEM) to evaluate the dynamics of rideshare demand in Chicago by analyzing data from 77 community areas over a 60-day period in 2022. Our modified SEM accounts for both spatial dependencies and temporal correlations. This study provides a nuanced understanding of how demographic, socioeconomic, and infrastructural factors impact rideshare usage. Our results indicate that population size, crime rates, and educational attainment are positively correlated with rideshare demand, whereas median age has a negative impact. Additionally, high transit accessibility enhances rideshare usage, suggesting a synergistic relationship with public-transportation systems. However, regions with high walkability showed reduced demand, indicating a preference for walking, or cycling over ridesharing in easily navigable areas. These insights are essential for urban planners and policymakers aiming to improve urban mobility and effectively integrate ridesharing into transportation ecosystems.