Abstract: Systems and methods for generating predicted preferences are disclosed. The method includes implementing, with a computing device having a processor and a non-transitory computer-readable memory, a conjoint architecture comprising: an autoencoder trained to transform input data including one or more choices and one or more features into a latent representation, and a choice classification network trained to predict one or more predicted preferences from the latent representation extracted by the autoencoder. The method further includes outputting, from the choice classification network, the one or more predicted preferences.

Abstract: A system and method for optimization of on-demand microtransit is provided. A list of possible stops of one or more vehicles is maintained. A plurality of requests for transportation are received, each of the requests associated with at least one traveler. Travelers to be transported by one of the vehicles are selected. A set of a minimal number of the stops is selected, the set comprising at least one stop that is within a predefined walking distance of the origin location of each of the selected travelers and at least one stop within the predefined walking distance of the destination location of each of the selected travelers. Potential routes are identified for the vehicle that include the stops in the set. The potential routes are evaluated using a plurality of constraints and one of the routes is selected for fulfilling the requests of the selected travelers.

Abstract: A system and method for optimization of on-demand microtransit is provided. A list of possible stops of one or more vehicles is maintained. A plurality of requests for transportation are received, each of the requests associated with at least one traveler. Travelers to be transported by one of the vehicles are selected. A set of a minimal number of the stops is selected, the set comprising at least one stop that is within a predefined walking distance of the origin location of each of the selected travelers and at least one stop within the predefined walking distance of the destination location of each of the selected travelers. Potential routes are identified for the vehicle that include the stops in the set. The potential routes are evaluated using a plurality of constraints and one of the routes is selected for fulfilling the requests of the selected travelers.

Abstract: One embodiment of the present invention provides a system for providing assistance to a user of a product in diagnosing faults in the product. During operation, the system receives, at a help server, data associated with current and/or past operation of the product; performs an optimization to determine a sequence of diagnostic actions that is expected to maximize a net benefit to the user. The sequence of diagnostic actions includes one or more actions that require the user to perform at least one task, and performing the optimization involves accounting for costs to the user for performing the at least one task and savings to the user for correcting the faults. The system then interacts with the user, which involves presenting the sequence of diagnostic actions to the user.

Abstract: One embodiment of the present invention provides a system for providing assistance to a user of a product in diagnosing faults in the product. During operation, the system receives, at a help server, data associated with current and/or past operation of the product; performs an optimization to determine a sequence of diagnostic actions that is expected to maximize a net benefit to the user. The sequence of diagnostic actions includes one or more actions that require the user to perform at least one task, and performing the optimization involves accounting for costs to the user for performing the at least one task and savings to the user for correcting the faults. The system then interacts with the user, which involves presenting the sequence of diagnostic actions to the user.