In an approach to creating and using a reinforcement learning model for personalizing a recommendation of a parking spot, one or more computer processors receive a first destination associated with the vehicle. One or more computer processors determine a parking spot availability in proximity to the destination. One or more computer processors determine a recommended parking spot location. One or more computer processors display the recommended parking spot location to the user. One or more computer processors determine a first parking spot selection. One or more computer processors receive a first satisfaction rating associated with the recommended parking spot location.