Optimizing Campus Parking and Reducing Congestion Through Machine Learning

Campus parking is a common problem that one faces in other organisations of learning. As such, it leads to bottlenecks, wastage of resources, and delays for the students, staff, and visitors. This paper investigates how the problem of campus parking can be addressed and improved by machine learning (ML) technologies. Parking management systems incorporated with cameras and sensors can allow applications of machine learning to be used to estimate parking lot bank availability, allocate parking resources and direct cars to the best possible locations. This work brings together results obtained from using advanced ML models like decision trees, support vector machines, and neural networks to create a model which can be used to vary the advice on available parking space depending on the traffic, time of the day and the level of occupancy. The objective is to assist in the timely availability of parking space at the campus, effective management of the parking areas to minimise wastage of space and reduction of the traffic flow within the campus parking areas. Furthermore, the possible benefits of the use of predictive modelling and analytics for parking infrastructure development and operational management are explored in the paper. Finally, it is established that the implementation of machine learning in the development of the parking system significantly increases the level of mobility on campus, helps to reduce the rush hour traffic and makes the functioning of the campus eco-friendlier.