Abstract: An example computer-implemented method includes accessing service request data indicative of a service request, the service request having a service type and one or more service parameters. The method includes computing a complexity score associated with the service request based on the service type and the one or more service parameters. The method includes selecting a first courier of a plurality of candidate couriers based on the complexity score associated with the service request. The method includes outputting first instructions to a first courier device associated with the first courier. The first instructions are executable by the first courier device to cause a service assignment to be provided for display via a user interface of the first courier device, the service assignment indicating the first courier is to perform the service request.

Abstract: Systems and methods for determining out-of-stock predictions for merchant items and performing intervention actions based on the out-of-stuck predictions using machine-learned models. The method includes obtaining feature data including at least (i) aggregations of historical found rate data, (ii) item level metadata, and (iii) merchant signal data into an out-of-stock model. The method includes determining a number of output scores for a number of items. The output scores can be indicative of a likelihood of an item being out-of-stock. The method includes determining a first output score for a first item of the plurality of items satisfies an intervention criterion. The method includes responsive to determining the first output score satisfies the intervention criterion, performing an intervention action.

Abstract: In one embodiment, a data processing method comprises generating impression estimate data that specifies an estimated total number of impressions of a plurality of non-program media items that are possible during future transmission of a plurality of media programs via a plurality of media channels; based on the impression estimate data, generating campaign data specifying a target number of impressions of a particular non-program media item and specifying one or more particular media channels to receive the particular non-program media item; based on the campaign data, and based upon transmission schedule data that specifies future times of transmission of the plurality of media programs via the plurality of media channels, automatically determining digitally stored promotional schedule data that specifies a plurality of times to transmit the particular non-program media item to achieve the target number of impressions; wherein the method is performed by one or more computing devices.

Abstract: In one embodiment, a data processing method comprises generating impression estimate data that specifies an estimated total number of impressions of a plurality of non-program media items that are possible during future transmission of a plurality of media programs via a plurality of media channels; based on the impression estimate data, generating campaign data specifying a target number of impressions of a particular non-program media item and specifying one or more particular media channels to receive the particular non-program media item; based on the campaign data, and based upon transmission schedule data that specifies future times of transmission of the plurality of media programs via the plurality of media channels, automatically determining digitally stored promotional schedule data that specifies a plurality of times to transmit the particular non-program media item to achieve the target number of impressions; wherein the method is performed by one or more computing devices.

Abstract: In one embodiment, a data processing method comprises generating impression estimate data that specifies an estimated total number of impressions of a plurality of non-program media items that are possible during future transmission of a plurality of media programs via a plurality of media channels; based on the impression estimate data, generating campaign data specifying a target number of impressions of a particular non-program media item and specifying one or more particular media channels to receive the particular non-program media item; based on the campaign data, and based upon transmission schedule data that specifies future times of transmission of the plurality of media programs via the plurality of media channels, automatically determining digitally stored promotional schedule data that specifies a plurality of times to transmit the particular non-program media item to achieve the target number of impressions; wherein the method is performed by one or more computing devices.

Abstract: In one embodiment, a data processing method comprises generating impression estimate data that specifies an estimated total number of impressions of a plurality of non-program media items that are possible during future transmission of a plurality of media programs via a plurality of media channels; based on the impression estimate data, generating campaign data specifying a target number of impressions of a particular non-program media item and specifying one or more particular media channels to receive the particular non-program media item; based on the campaign data, and based upon transmission schedule data that specifies future times of transmission of the plurality of media programs via the plurality of media channels, automatically determining digitally stored promotional schedule data that specifies a plurality of times to transmit the particular non-program media item to achieve the target number of impressions; wherein the method is performed by one or more computing devices.