Abstract: A method, system and computer program product for data deduplication in a travel and transportation data processing system includes loading into memory for comparison from a database of a multiplicity of multi-field records, a pair of two different multi-field records and submitting the pair to a similarity model that correlates a companion passenger with a specified individual so as to indicate a probability of duplication whenever the companion passenger appears in a pair of records submitted to the model for comparison. Thereafter, if the model produces a high probability, the pair is automatically merged into a single record without manual intervention, but if the model produces a medium probability, the pair is placed in a queue pending manual intervention and manual merging, and if the similarity model produces a low probability, the pair is omitted from consideration of merging. Finally, the process repeats for each other pair of different multi-field records in the database.

Abstract: A method, system and computer program product for data deduplication in a travel and transportation data processing system includes loading into memory for comparison from a database of a multiplicity of multi-field records, a pair of two different multi-field records and submitting the pair to a similarity model that correlates a companion passenger with a specified individual so as to indicate a probability of duplication whenever the companion passenger appears in a pair of records submitted to the model for comparison. Thereafter, if the model produces a high probability, the pair is automatically merged into a single record without manual intervention, but if the model produces a medium probability, the pair is placed in a queue pending manual intervention and manual merging, and if the similarity model produces a low probability, the pair is omitted from consideration of merging. Finally, the process repeats for each other pair of different multi-field records in the database.

Abstract: A method for predicting risk in a tour operation includes first ingesting into memory of a computing system, textual observations from past tour operations and then correlating the textual observations to a corresponding one of the past tour operations. Thereafter, each of the past tour operations may be classified according to risk to personal safety and each correlation and an associated risk may be stored in an index. Consequently, tour commentary of a contemporaneously offered tour may be later loaded into memory of the computing system, and the terms of the tour commentary matched to the textual observations of at least one of the past tour operations. Finally, an associated risk is retrieved for an entry in the index corresponding to the at least one of the past tour operations, a predicted risk is computed based upon the retrieved risk value, and the predicted risk is displayed in a display of the computing system in connection with the contemporaneously offered tour.

Abstract: Embodiments of the invention provide a method, system and computer program product for voyage-level prediction of a net promoter score (NPS) data set for a collection of passengers scheduled for transport by a vehicle. The method includes classifying a past set of completed voyages according to a discrete set of classifications, each referring to a different characteristic of a corresponding one of the completed voyages, ingesting survey responses from passengers of the completed voyages and correlating the responses to an associated one of the different classifications, scheduling a new voyage for a specific vehicle, determining a set of classifications for the new voyage, extrapolating hypothetical survey responses for the new voyage based upon the determined set of classifications for the new voyage and displaying the hypothetical survey responses in a display of an onboard computing system of the specific vehicle.