Cluster-based analysis of parking satisfaction and strategies

The accelerating discrepancy between the demand for parking spaces and their availability is a critical aspect of urban infrastructure that often leads to traffic congestion and user dissatisfaction. This issue is particularly acute on college campuses, where expanding enrollments and limited expansions in parking capacity exacerbate congestion, affecting daily commutes and the overall campus environment. The literature lacks comprehensive studies that explore how various demographic variables coalesce to form distinct user groups with unique parking needs and perceptions. This study aims to fill that void by offering targeted parking management strategies tailored to the specific requirements of distinct user clusters, thereby elevating overall parking satisfaction for all. To achieve this goal, a robust methodology was employed that entailed conducting a survey and gathering responses from 873 individuals (students, faculty, and staff at the University of Texas at Arlington). The questions delved into various aspects of travel and parking behaviors, level of satisfaction with parking facilities, and sociodemographic characteristics. A hierarchical clustering approach, followed by K-means clustering, was used to identify homogenous respondent groups and resulted in three distinct clusters being categorized. The findings revealed stark differences in parking satisfaction levels across these clusters that were influenced by factors such as the degree of difficulty in finding parking, the distance from residence to parking, and perceptions of the enforcement of parking rules. Notably, the study highlights a general openness among all groups to adopting AI-powered parking solutions, which indicates a shift towards technology-driven improvements in parking management. This research holds valuable implications for university administrators, urban planners, and transportation policymakers seeking to enhance parking satisfaction and efficiency.