Abstract: A system and method for video authentication may apply machine learning to analyze whether a person's face captured by live video matches a face in a photo ID captured by live video and to analyze other features based on a video session with the person. For example, machine learning may be applied to analyze a set of features indicating whether the person is a real, live person (as opposed to a photo image held up over the person's face in the video, etc.). Finally, the machine learning may be applied to analyze a set of features to determine whether a lower probability prediction that the person's face captured by live video matches a face in a photo ID captured by live video should be either pass authentication (due to one or more features/circumstances mitigating the lower probability) or fail authentication (due to one or more features not mitigating the lower probability). In such a situation, the set of features may indicate that mitigating factors/conditions exist that can offset the lower probability.

Abstract: A system and method for video authentication may apply machine learning to analyze whether a person's face captured by live video matches a face in a photo ID captured by live video and to analyze other features based on a video session with the person. For example, machine learning may be applied to analyze a set of features indicating whether the person is a real, live person (as opposed to a photo image held up over the person's face in the video, etc.). Finally, the machine learning may be applied to analyze a set of features to determine whether a lower probability prediction that the person's face captured by live video matches a face in a photo ID captured by live video should be either pass authentication (due to one or more features/circumstances mitigating the lower probability) or fail authentication (due to one or more features not mitigating the lower probability). In such a situation, the set of features may indicate that mitigating factors/conditions exist that can offset the lower probability.

Abstract: A device may receive first information relating to a first set of transactions and a first set of chargebacks associated with the first set of transactions; process the first information to generate a processed data set; train a model to perform classification of the first set of chargebacks, where the model is to receive, as input, information relating to transactions and at least one chargeback, and where the model is to output information identifying a classification of the at least one chargeback; receive second information identifying a second set of transactions and a second set of chargebacks associated with the second set of transactions, where the second information is received from multiple, different sources; determine a classification of the second set of chargebacks using the model and based on the second information; and perform an action based on the classification of the second set of chargebacks.

Abstract: A device may receive first information relating to a first set of transactions and a first set of chargebacks associated with the first set of transactions; process the first information to generate a processed data set; train a model to perform classification of the first set of chargebacks, where the model is to receive, as input, information relating to transactions and at least one chargeback, and where the model is to output information identifying a classification of the at least one chargeback; receive second information identifying a second set of transactions and a second set of chargebacks associated with the second set of transactions, where the second information is received from multiple, different sources; determine a classification of the second set of chargebacks using the model and based on the second information; and perform an action based on the classification of the second set of chargebacks.