A marketing analytics pipeline includes an opportunity detection analytics hub and a marketing platform, wherein the opportunity detection analytics hub is configured to use trend data reports from a consumption database to fit statistical models based on streaming consumption and interaction patterns of social media UGC (user generated content) and to send growth and re-engagement opportunities to a marketing action analytics hub, and wherein the marketing platform is configured to interact with the marketing action analytics hub to create targeted marketing campaigns based around high growth potential audiences. In a further aspect, the opportunity detection analytics hub includes an offline prediction model generation component and an online opportunity detection component that receives both current streaming consumption and social media UGC interaction data for a plurality of media IP assets and identifies opportunities from the combination of these two data sources that could not be detected if analyzed separately, inclusive of a case where significant changes are detected in social media UGC interaction patterns, but are not yet detected in streaming consumption.

Method and systems for scheduling tasks to field professionals include: receiving a request to book a new appointment for a service, wherein the service is expected to be completed within a time period; identifying a first possible time slot and a subsequent second possible time slot for the new appointment within the time period; calculating a first scheduling cost associated with the first possible time slot and a second scheduling cost associated with the second possible time slot; enabling selection of the second possible time slot when it is determined that both the first scheduling cost and the second scheduling cost are below a scheduling cost threshold; and outputting a no-available-time-slot notification when is determined that both the first scheduling cost and the second scheduling cost are above the scheduling cost threshold.

An online concierge system allows users to order items within discrete time intervals later than a time when an order was received or for short-term fulfillment when the order was received. To account for a number of shoppers available to fulfill orders during different discrete time intervals and numbers of orders for fulfillment during different discrete time intervals, the online concierge system specifies a target rate for orders fulfilled later than a specified discrete time interval and a threshold from the target rate. A trained machine learning model periodically predicts a percentage of orders being fulfilled late, with an order associated with a predicted percentage when the order was received. The online concierge system increases a price of orders associated with predicted percentages greater than the threshold from the target rate. The increased price of an order is determined from a price elasticity curve and the predicted percentage.

In one embodiment, a computer-implemented method includes acquiring sequential user behavior data including one-dimensional data. The user behavior data is associated with a user. The method includes abstracting features from the sequential user behavior data to cover short-term and long-term timeframes. The method includes determining one or more properties of the user based on the features.

Techniques for preparing datasets for geo experiments and improving accuracy of geo experiments are presented herein. The system can access a dataset of a plurality of geographic pairs. Additionally, the system can calculate a first outcome estimate based on a difference in response data and a difference in input data for a first geographic pair. Moreover, the system can calculate a plurality of experimental uncertainty estimates associated with the plurality of geographic pairs during an experimental time interval. The system can access historical data associated with the plurality of geographic pairs. Furthermore, the system can determine a beta value and a trim rate that reduces a sum of the plurality estimates. Subsequently, the system can remove, based on the first outcome estimate and the beta value, the first geographic pair from the plurality of geographic pairs to generate the first subset of geographic pairs.

Systems, methods, computing platforms, and storage media for providing image recommendations are disclosed. Exemplary implementations may: receive a set of images; access a context segment graph comprising one or more nodes; identify a subset of images related to a node in the context segment graph; receive one or more user responses for the subset of images; generate one or more models based on the user responses; receive one or more candidate images for a creative campaign; determine, using at least one model, a relatedness value and a responsiveness value for at least a portion of the one or more candidate images; and display a listing of the plurality of candidate images, wherein the listing includes, for each candidate image, a confidence score and one or more of the relatedness and responsiveness values in context to the node.

Systems and methods for features engineering, in which internal and external signals are received and fused. The fusing is based on meta-data of each of the one or more internal signals and each of the one or more external signals. A set of features is generated based on one or more valid combinations that match a transformation input, the transformation forming part of library of transformations. Finally, a set of one or more features is selected from the plurality of features, based on a predictive strength of each feature. The set of selected features can be used to train and select a machine learning model.

Systems as described herein may include making recommendations for patterned purchases. Transaction information for a user that is associated with a plurality of merchants in a geographic location may be received. Frequencies of visits and transaction patterns associated with the plurality of merchants may be determined. Risk factors and a success rate that the user to complete shopping successfully may be determined. In a variety of embodiments, after detecting that the success rate falls below a threshold value, a recommendation for the user to shop at an alternative merchant and alternative time/date may be presented to the user.

A method, apparatus and product including: assigning geographical zones to a mobile retail unit based on first user segments of customers from the geographical zones and based on second user segments associated to an inventory of the mobile retail unit; based on the mobile retail unit being located at a location in the geographical zones, detecting a first group of customers within a first distance threshold from the location; sending a first set of order invitations to the first group of customers; determining to adjust the first distance threshold based on a delay probability; based on said determining, increasing the first distance threshold to a second distance threshold, wherein a second group of customers are detected within the second distance threshold; and sending a second set of order invitations to the second group of customers.

A method and a system dynamically adapt a passenger transport capacity of a transport line to the number of passengers determined for the transport line. The system contains a main evaluator configured for automatically determining, as a function of the time, the number of passengers for the transport line, and a processor configured for acquiring the number of passengers as a function of the time, a nominal timetable, and a nominal passenger transport capacity of each vehicle of the line. The processor applies a trained function to the number of passengers, and the trained function has been trained by a machine learning algorithm for predicting a future temporal evolution of the number of passengers. The processor is configured for determining a measure for adapting the transport capacity of the line to the future temporal evolution. The system is further configured for applying the measure to the transport line.