Enhancing Urban Parking Efficiency Through Machine Learning Model Integration

Abstract

An increase in vehicular traffic and a scarcity of parking spaces are creating significant challenges for urban parking management. This study aims to tackle these issues that escalate congestion and pollution and decrease urban productivity, by utilizing machine learning models to accurately predict parking space availability and categorize occupancy levels. It employs a dataset from a college campus garage collected from January 2022 to June 2023 and analyzes the performance of random forest, decision tree, linear regression, and support vector models by comparing them, using multiple evaluation metrics. The results revealed that the random forest model was the most reliable, as it demonstrated strong performance in both the regression and classification analyses and was adept at estimating the exact number of available parking spaces. A concurrent classification analysis that categorized parking occupancy into different levels proved valuable for enhancing the quality of communication and decision-making. An analysis of the importance of various features clearly highlighted the influence of the day of the week on parking demand and patterns; the impact of seasonality on the volume of parking usage; and the time of day, which plays a crucial role in determining parking behavior. The research will benefit urban planners, facility managers, and policymakers by providing them with insights and tools that will enhance the urban parking experience and address the complex challenges of modern urban environments.

Keywords

• Parking management
• predictive modeling
• random forest model
• decision tree
• support vector machine
• linear regression