Abstract: A computer product and method for autonomously renting equipment with a machine learning model that is trained on a set of positive image pairs and a set of negative image pairs from prior rental transactions, each pair of images consisting of an image of a driver license and an image of a selfie photograph (“selfie”). The method includes receiving a computer communication from a renter that includes a rental request to rent the equipment for a rental duration. The renter is prompted to submit renter data that includes a selfie while holding his or her driver license. The selfie is preprocessed to generate a new image pair comprising an image of the renter's driver license and an image of the renter's selfie. Machine learning is employed to inference a first probability that both images in the new image pair are images of the same person. Upon determining that the probability inference is less than a predetermined threshold value, the rental request is denied.