Abstract: Computer-implemented methods of providing personalized recommendations to a user of items available in an online system, and related systems. First-level features including context features are computed based upon context data. A first-level machine learning model is then evaluated using the first-level features to generate predictions of user behavior in relation to a plurality of individual items available via the online system. A list of proposed item recommendations is constructed based upon the predictions. Second-level features are computed based upon the context data and list features based upon the list of proposed item recommendations and the corresponding predictions generated by the first-level machine learning model. A second-level machine learning model is evaluated using the second-level features to generate a prediction of user behavior in relation to the list of proposed item recommendations.

Abstract: Methods of reinforcement learning for a resource management agent. Responsive to generated actions, corresponding observations are received. Each observation comprises a transition in a state associated with an inventory and an associated reward in the form of revenues generated from perishable resource sales. A randomized batch of observations is periodically sampled according to a prioritized replay sampling algorithm. A probability distribution for selection of observations within the batch is progressively adapted. Each batch of observations is used to update weight parameters of a neural network that comprises an approximator of the resource management agent, such that when provided with an input inventory state and an input action, an output of the neural network more closely approximates a true value of generating the input action while in the input inventory state. The neural network may be used to select each generated action depending upon a corresponding state associated with the inventory.

Abstract: Computer-implemented methods of providing personalized recommendations to a user of items available in an online system, and related systems. First-level features including context features are computed based upon context data. A first-level machine learning model is then evaluated using the first-level features to generate predictions of user behavior in relation to a plurality of individual items available via the online system. A list of proposed item recommendations is constructed based upon the predictions. Second-level features are computed based upon the context data and list features based upon the list of proposed item recommendations and the corresponding predictions generated by the first-level machine learning model. A second-level machine learning model is evaluated using the second-level features to generate a prediction of user behavior in relation to the list of proposed item recommendations.

Abstract: Systems, methods, and computer program products for mining search query logs. A data warehousing system includes a query database that stores data relating to search queries, a reservation history database that stores data relating to booked products, and a data warehousing application that extracts and processes the search query and booking data from the query and reservation history databases to produce statistical data. The data warehousing application generates historical query, booking, and specific flight booking pickup curves based on the extracted statistical data. A weighted average of the historical query and booking pickup curves is determined that provides a best fit with the flight specific pickup curve. A weighting factor that produced the best fit is then used to forecast demand for future flights.

Abstract: Methods, systems, and program products for assigning scheduled vehicles to stands. First and second vehicles each have a scheduled arrival time and a scheduled departure time. A minimum buffer time between a departure of the first vehicle and an arrival of the second vehicle is calculated based on a distribution of a deviation from the scheduled departure time of the first vehicle and/or on a distribution of a deviation from the scheduled arrival time of the second vehicle. The first vehicle and the second vehicle are assigned to different ones of the stands in response to the time interval between the scheduled departure time of the first vehicle and the scheduled arrival time of the second vehicle being less than the minimum buffer time.