Abstract: A set of payment card transactions including a sparse set of fraudulent transactions is normalized, such that continuously valued literals in each of the set of transactions are transformed to discrete literals. The normalized transactions are used to train a classifier, such as a neural network, such that the classifier is trained to classify transactions as fraudulent or genuine. The fraudulent transactions in the set of payment card transactions are clustered to form a set of prototype transactions. Each of the discrete literals in each of the prototype transactions is expanded using sensitivity analysis using the trained classifier as an oracle, and a rule for identifying fraudulent transactions is generated for each prototype transaction based on the transaction's respective expanded literals.

Abstract: A set of payment card transactions including a sparse set of fraudulent transactions is normalized, such that continuously valued literals in each of the set of transactions are transformed to discrete literals. The normalized transactions are used to train a classifier, such as a neural network, such that the classifier is trained to classify transactions as fraudulent or genuine. The fraudulent transactions in the set of payment card transactions are clustered to form a set of prototype transactions. Each of the discrete literals in each of the prototype transactions is expanded using sensitivity analysis using the trained classifier as an oracle, and a rule for identifying fraudulent transactions is generated for each prototype transaction based on the transaction's respective expanded literals.

Abstract: The invention relates, in various aspects, to systems and methods for detecting fraudulent transactions. A server receives transaction data corresponding to a plurality of customer-not-present (“CNP”) transactions, after a first batch process and before a second batch process. A real-time fraud detection processor is configured for processing the transaction data and data obtained during the first batch process and, for each CNP transaction, outputting an authorization decision of the respective CNP transaction. A batch fraud detection processor is configured for executing the second batch process by collectively processing the transaction data and data obtained during the processing of the transaction data by the real-time fraud detection processor.