Abstract: The valet parking system is made up of carefully built yet simple-to-use software apps that allow even the most technologically challenged persons to access ride-on-demand services. As a result of our findings, we now realise the necessity for an on-demand valet service system in India's metropolitan centres, where the population is growing and car traffic is expanding. This project creates an architecture based on the Firebase Cloud Messaging (FCM) technology and introduces a novel algorithm that provides a valet parking system. This cost will be used to provide a solution for identifying an available valet service provider in response to a user's request, as well as a solution for proposing a new valet service provider if the present valet service provider refuses the request or no one is available to serve at the time. The simulation findings suggest that the algorithm assists users in receiving on-demand valet service and reduces the time spent looking for parking in real time. We will also be successful in putting the planned system into practice.Keywords: car parking, valet, machine learning, k nearest neighbor, android, java, etc