Abstract: A method may include receiving, by at least one processor associated with a financial institution, a purchase transaction information of a purchase of at least one airline ticket from a flight booking database. The purchase transaction information may be associated with an account of a payment card issued by a financial institution. A travel advisory may automatically be applied to the account of the payment card based on a first destination location and a first departure date of the at least one airline ticket. The at least one processor may establish an airline reservation modification trigger event in the flight booking database and may receive the modified airline reservation information from the flight booking database when the airline reservation information was modified. The travel advisory may be updated for the account of the payment card issued by the financial institution in accordance with the modified airline reservation information.

Abstract: Disclosed herein are system, method, and computer program product embodiments for generating labels for training a machine learning mode using an incremental time window process. The described process may be used in a recurrence detection system. A dataset may be analyzed using incremental split dates to divide the dataset into an analysis portion and a holdout portion. The analysis portion may be analyzed to determine input features related to a predicted recurrence in the dataset. The holdout portion may be tested against the analysis portion and the input features to generate a label. The label may indicate whether or not the holdout portion confirms the prediction. The testing of the holdout portion against the analysis portion may be repeated by incrementally using different split dates and multiple separate analysis portions and holdout portions to generate multiple labels and corresponding input features.

Abstract: Disclosed herein are system, method, and computer program product embodiments for generating labels for training a machine learning mode using an incremental time window process. The described process may be used in a recurrence detection system. A dataset may be analyzed using incremental split dates to divide the dataset into an analysis portion and a holdout portion. The analysis portion may be analyzed to determine input features related to a predicted recurrence in the dataset. The holdout portion may be tested against the analysis portion and the input features to generate a label. The label may indicate whether or not the holdout portion confirms the prediction. The testing of the holdout portion against the analysis portion may be repeated by incrementally using different split dates and multiple separate analysis portions and holdout portions to generate multiple labels and corresponding input features.

Abstract: A method may include receiving, by at least one processor associated with a financial institution, a purchase transaction information of a purchase of at least one airline ticket from a flight booking database. The purchase transaction information may be associated with an account of a payment card issued by a financial institution. A travel advisory may automatically be applied to the account of the payment card based on a first destination location and a first departure date of the at least one airline ticket. The at least one processor may establish an airline reservation modification trigger event in the flight booking database and may receive the modified airline reservation information from the flight booking database when the airline reservation information was modified. The travel advisory may be updated for the account of the payment card issued by the financial institution in accordance with the modified airline reservation information.

Abstract: Disclosed herein are system, method, and computer program product embodiments for generating labels for training a machine learning mode using an incremental time window process. The described process may be used in a recurrence detection system. A dataset may be analyzed using incremental split dates to divide the dataset into an analysis portion and a holdout portion. The analysis portion may be analyzed to determine input features related to a predicted recurrence in the dataset. The holdout portion may be tested against the analysis portion and the input features to generate a label. The label may indicate whether or not the holdout portion confirms the prediction. The testing of the holdout portion against the analysis portion may be repeated by incrementally using different split dates and multiple separate analysis portions and holdout portions to generate multiple labels and corresponding input features.