Abstract: Systems, methods and computer program products associated with a flight search engine for searching itineraries between an origin and a destination on a given date, according to a predefined display policy. Available routes may be filtered according to a first set of predefined criteria associated with the routes. The filtered available routes may be ranked according to a second set of predefined criteria. Itineraries may be constructed that are associated with the filtered available routes. The constructed itineraries may be filtered according to a third set of predefined criteria, and the filtered itineraries may be ranked according to a fourth set of predefined criteria. Historical booking data regarding previously booked itineraries for future travels may be received and analyzed, and may be taken into in the ranking of the filtered available routes and the filtered itineraries.

Abstract: Systems, methods and computer program products associated with a flight search engine for searching itineraries between an origin and a destination on a given date, according to a predefined display policy. Available routes may be filtered according to a first set of predefined criteria associated with the routes. The filtered available routes may be ranked according to a second set of predefined criteria. Itineraries may be constructed that are associated with the filtered available routes. The constructed itineraries may be filtered according to a third set of predefined criteria, and the filtered itineraries may be ranked according to a fourth set of predefined criteria. Historical booking data regarding previously booked itineraries for future travels may be received and analyzed, and may be taken into in the ranking of the filtered available routes and the filtered itineraries.

Abstract: Systems, methods, and computer program products for monitoring a first database. A database monitoring system receives data indicative of change events relating to records in the first database, and stores the events in a second database. The database monitoring system further identifies records associated with fraudulent transactions, and defines a training set of transactions that includes the fraudulent transactions. A neural network is trained to detect patterns of events indicative of fraud using the training set and the corresponding events stored in the second database. In response to the trained neural network detecting a fraudulent pattern of events associated with an active database record, the database monitoring system analyzes the underlying transaction to determine if the transaction is fraudulent. A graphical display may be generated based on data extracted from the neural network, and may depict one or more vertices corresponding to events associated with fraudulent transactions.

Abstract: Systems, methods, and computer program products for processing transactions in a transaction queue. Transactions selected for further review are positioned within the transaction queue based on a priority level. The priority level is determined based on expected reduction in a cost of fraud for reviewing the transaction as compared to accepting the transaction without performing the review. The capacity to review transactions is adjusted to accommodate the expected number of transactions that have a higher reduction in cost of fraud than the opportunity cost of performing the review. To account for cases in which a transaction selected for review cannot be reviewed prior to the capture time, a probability is determined that the transaction will not be reviewed, and the cost of fraud for requesting the review adjusted based thereon.

Abstract: Methods, systems, and computer program products for screening a request for a transaction to purchase a travel service. Based on one or more of a probability of fraud for the transaction, a probability distribution for receiving a chargeback with respect to time if the request is accepted, a probability distribution with respect to time for completing a security check, a probability that the travel service will be rebooked if the request is denied, and a bid-price for a travel service, a revenue management system determines a future revenue impact for accepting, denying, or requesting a security check on the request. The future revenue impact is used to adjust a total cost of fraud for the transaction. The revenue management system may then determine whether the request should be accepted, denied, or subjected to the security check based on the expected future revenue impact and the expected cost of fraud.

Abstract: Methods, systems, and computer program products for screening transactions. Transactions stored in a transaction database may provide a statistical basis for determining a probability of fraud for a pending transaction. The cost of fraud may be determined for each of a plurality of possible actions based on the probability of fraud, and the action that provides the lowest cost of fraud chosen. A cumulative cost of fraud may be determined for a set of transactions in the database. If taking the action with the lowest cost of fraud for the transaction would result in a higher cumulative cost of fraud, an action having the higher cost of fraud for the transaction may be chosen. The transaction may be added to the database, and the probability of fraud adjusted based on an amount of time since acceptance of the transaction. The statistical basis may be optimized based on a cost error.

Abstract: Methods, systems, and computer program products for screening transactions. Transactions stored in a transaction database may provide a statistical basis for determining a probability of fraud for a pending transaction. The cost of fraud may be determined for each of a plurality of possible actions based on the probability of fraud, and the action that provides the lowest cost of fraud chosen. A cumulative cost of fraud may be determined for a set of transactions in the database. If taking the action with the lowest cost of fraud for the transaction would result in a higher cumulative cost of fraud, an action having the higher cost of fraud for the transaction may be chosen. The transaction may be added to the database, and the probability of fraud adjusted based on an amount of time since acceptance of the transaction. The statistical basis may be optimized based on a cost error.

Abstract: Methods, systems, and computer program products for screening transactions. A probability function provides an estimated probability of fraud for a pending transaction based on one or more parameters of the transaction. The estimated probability of fraud is used to determine an estimated cost of fraud for several possible actions that may be taken with regard to the transaction, and the action that provides the lowest expected cost of fraud chosen. To reduce prediction error, the function is adjusted to minimize a “cost error”, which is determined by applying the function to historical transactions stored in a transaction database. The cost error may be determined by comparing estimated probabilities of fraud for accepted transactions to a known probability of fraud based on whether a chargeback was received for the transaction in question. Parameters of the function may be adjusted to minimize a collective cost error across a set of historical transactions.

Abstract: Methods, systems, and computer program products for handling a payment strategy for a payment platform of an airline merchant. One or more alternatives are determined for each category. Each alternative includes at least one of the one or more payment items. Transactions are received for different combinations of the alternatives. Financial impacts are determined for each simulated transaction based on the financial parameters. Based on the financial impacts, one of the combinations of the alternatives is determined to be the payment strategy for the payment platform.