As proposed by the increasing requirement for the effective infrastructure of the public transportation systems, the solution is to implement new technologies. This research aims to analyze the relationship between IoT and ML to enhance smart public transit systems. IoT sensors and GPS on transit vehicles are used to get real-time information about the location of the cars, the number of passengers on board, and the traffic conditions. The research aims to enhance the routing and scheduling systems, efficiency, and customer satisfaction levels. The quantitative research approach involves evaluating the level of service delivery offered by transportation services through simulated studies through parameters such as average travel time, percentage of on-time arrival among others, and the utilization rates of employed resources. Some examples of modern machine learning techniques used in making these predictions and changing services based on the given conditions include linear regression and decision trees. Based on the available first outcome, it has been realized that the efficiency of the system and user satisfaction touch a new high whenever IoT and ML are integrated. This work also identifies the current gaps in the research and proposes other potential development directions for incorporating technology into public transit systems. Taking into account all the points discussed, the integration of IoT and ML is a groundbreaking approach that creates the possibility of looking for a better and more efficient urban transport system.