Predictive analysis of parking behavior after implementation of smart parking system

Expanding urban landscapes and the ever-increasing number of vehicles on the road make it challenging for drivers to find a convenient place to park and result in even more traffic congestion and higher levels of pollution. Smart parking systems (SPS) offer a transformative solution by providing real-time data that can significantly enhance the efficiency of parking experiences and management, especially in densely populated areas like university campuses. Despite the advent of SPS, however, there's a gap in the research on how it affects drivers' compliance and behavior. To address this gap, this study investigates SPS's impact in a university setting by predicting and analyzing the parking citations that were issued after its implementation. The methodology involved analysis of data from the past six years and the application of a long-short term memory network for predictive modeling, employing features such as time of day, day of the week, and campus events. The study's results demonstrate a clear reduction in the number of parking violations compared to the model's predictions and highlight the positive impact of SPS on improving parking management and user compliance. Statistically significant findings from the Kolmogorov-Smirnov test support the effectiveness of SPS and indicate a substantial enhancement in parking behavior post-implementation. These outcomes reveal the potential of SPS to ease urban congestion and contribute to the overall sustainability of city landscapes. The study also highlights the role of SPS in fostering behavioral changes among users, promoting practices that are in line with sustainable transportation objectives, and advancing the efficiency of urban mobility. The findings of this study will foster the development of efficient and sustainable parking solutions for college campuses.