Abstract: A method including training a machine-learning model, based on historical data, with a maximization problem and one or more minimization problems to improve one or more fairness metrics. The method also can include receiving real-time data. The method additionally can include generating a risk score based on the machine-learning model, as trained, and the real-time data. Other embodiments are described.

Abstract: Methods and systems are described. A method includes accessing training data samples that includes a plurality of transaction laundering associated features and generating random samples, training a first plurality of different models to identify transaction laundering merchants based on random samples generated from each of the training data samples, training a second plurality of different models to identify the transaction laundering merchants based on the training data, generating a transaction laundering classification for a merchant from each of the first plurality of models and each of the second plurality of models, generating a first model group classification based on a first majority vote on transaction laundering classifications from the first plurality of models, and generating a second model group classification based on a second majority vote on transaction laundering classifications from the second plurality of models. A likelihood that the merchant is a transaction launderer is determined.

Abstract: Methods and systems are described. A method includes accessing training data samples that includes a plurality of transaction laundering associated features and generating random samples, training a first plurality of different models to identify transaction laundering merchants based on random samples generated from each of the training data samples, training a second plurality of different models to identify the transaction laundering merchants based on the training data, generating a transaction laundering classification for a merchant from each of the first plurality of models and each of the second plurality of models, generating a first model group classification based on a first majority vote on transaction laundering classifications from the first plurality of models, and generating a second model group classification based on a second majority vote on transaction laundering classifications from the second plurality of models. A likelihood that the merchant is a transaction launderer is determined.

Abstract: Described herein are systems and methods for providing accurate assessments of existing fraud rules while controlling for various transaction risks. In some embodiments, transaction data may be obtained from a number of entities and may be segmented by applying various filters. Once segmented, each segment may be analyzed to obtain metrics for a target entity. A separate set of peers is dynamically determined for each segment. The metric values for the target entity may then be compared to the metric values for the peers in the peer set to assess the target entity's performance with respect to each segment. Based on a variance of the target entity from its peers, the system may identify the segment as an opportunity. A rule may then be generated automatically based on the identified segment. In some embodiments, the rule may be added to a rule file for automatic implementation by the target entity.

Abstract: Described herein are systems and methods for providing accurate assessments of existing fraud rules while controlling for various transaction risks. In some embodiments, transaction data may be obtained from a number of entities and may be segmented by applying various filters. Once segmented, each segment may be analyzed to obtain metrics for a target entity. A separate set of peers is dynamically determined for each segment. The metric values for the target entity may then be compared to the metric values for the peers in the peer set to assess the target entity's performance with respect to each segment. Based on a variance of the target entity from its peers, the system may identify the segment as an opportunity. A rule may then be generated automatically based on the identified segment. In some embodiments, the rule may be added to a rule file for automatic implementation by the target entity.