Abstract: Systems and methods of operating smart notifications are disclosed. In one aspect, a method includes receiving, at a first time, a first request to transmit a first electronic message to a pilot account associated with an electronic device, and queuing the first electronic message without notification to the electronic device. The method also includes receiving, at a second time, a second request to transmit a second electronic message to the electronic device, and queuing the second electronic message without notification to the electronic device. The method further includes in response to identifying an end of the restricted period, transmitting, at a third time after the end of the restricted period, a third electronic message to the pilot account associated with electronic device, the third electronic message comprising an updated flight event in accordance with a first flight event and a second flight event.

Abstract: Embodiments described herein are related to systems and methods for offering an upgrade for a transportation service. In one aspect, a computer can receive a reservation request for a transportation service including an itinerary indicating a first location, a second location, and a first service category of the transportation service. The computer can determine a plurality of reposition estimates for a plurality of service categories including the first service category and one or more potential service categories, each reposition estimate being determined based upon the first location, the second location, and a particular service category. The computer can identify, as a second service category, the potential service category having the reposition estimate lower than the reposition estimate of the first service category in the reservation request. The computer can transmit to the client device an upgrade notification indicating an eligibility to update the itinerary to include the second service category.

Abstract: Embodiments described herein are related to systems and methods for forecasting demands for a transportation service. In one aspect, a set of neural network models may be implemented, where each neural network model can be configured to predict a booking status of a category of carriers on a corresponding date from a range of dates before a departure date. In one aspect, for each neural network model, a corresponding set of configuration values can be determined. Examples of the corresponding set of configuration values includes at least one of a number of layers, a number of neurons, and an activation function of the each neural network model. The set of neural network models can be constructed, according to corresponding sets of configuration values, and the constructed neural network models can be trained.