Abstract: Using a machine learning model(s) for fraud reduction is described. A payment service computing platform may receive, from an electronic device, user data associated with a user, and dynamically determine an incentive(s) associated with the user based on the user data. The incentive(s) may be determined using a trained machine learning model(s) that is trained based on previously collected user data. The payment service computing platform can then cause a user interface to be displayed via a payment application executing on the electronic device, wherein the user interface presents an interactive element(s) for receiving the incentive(s) in exchange for the user referring at least one other user to a payment service.