USING MACHINE LEARNING TO CLASSIFY INSURANCE CARD INFORMATION

An insurance management system receives, from a client device, at least one image of an insurance card associated with the user operating the client device. The insurance management system extracts features from the at least one image and generates a feature vector associated with the at least one image. A machine learning model receives the feature vector as input and outputs a classification comprising an association with an insurance plan. The insurance management system receives historical medical information that is specific to the user and indicates a current medical condition of the user and evaluates the insurance plan of the user in view of their historical medical information. Based on the evaluation, the insurance management system provides a recommendation that comprises one or more alternative insurance plans or one or more alternative pharmacies.