In some examples, a computer-implemented method of managing an advertising exchange is provided. The method uses email data and provides an interactive user interface for controlling management of data in an email channel. One or more inputs of online audience data is received. The online audience data includes email channel inventory from multiple publishers, Offline audience data including offline shopping behavior is sourced from at least one or more offline source. The online audience data and the offline audience data is included in a unified customer database, and the interactive user interface includes interface elements selectable to present online and offline audience data sourced from the unified customer database.

Systems and methods are disclosed for optimizing distribution of resources to data elements, comprising receiving a designation of one or more data elements for distribution; receiving a designation of a plurality of electronic event types detectable over a network, the plurality of electronic event types being associated with receipt or electronic display of at least one data element of the one or more data elements, to be tracked; forecasting a return on investment, associated with distribution of the one or more data elements, based on a forecast of occurrences of the plurality of electronic event types; and optimizing distribution of resources to the one or more data elements based on the forecasted return on investment.

According to an implementation, a method for digital information retrieval in a social media platform includes transmitting, over a network, information to render a timeline of social content for a user of a client application. The timeline of social content includes messages posted on the messaging platform by user accounts that are connected to a user account of the user in a connection graph. The method includes computing, using a machine-learning algorithm inputted with relevance signals, a relevance level between the user account of the user and a user account not linked to the user account of the user in the connection graph, and transmitting information about a profile of the user to a computing device associated with the user account not linked to the user account of the user in response to the relevance level being greater than a threshold level.

The SYNTHETIC CONTROL GENERATION AND CAMPAIGN IMPACT ASSESSMENT APPARATUSES, METHODS AND SYSTEMS (“SCG”) provides a platform that, in various embodiments, is configurable to evaluate efficacy and/or return on investment of advertising and/or other media campaigns and/or to recommend actions for improvement thereof. In some implementations, multi-faceted campaigns of media and/or advertising behavior (e.g., including one or more of: internet advertising, television advertising, radio advertising, print advertising, social media publication, product placement, and/or the like) may be considered as a whole in relation to global metric behaviors and/or patterns in order to evaluate the efficacy and/or return on investment associated with the campaign as a whole.

Systems and methods for the efficient generation and testing of promotions within a load to card environment are provided. A load-to-card abstraction layer collects store, user and offer data. The test promotions are then generated to span a design space of an offer. The user base is segmented and the test promotions are applied. The promotions include an offer, and the ability to load the offer for later redemption (load-to-card). Redemption and load rates are measured, and can be used individually, or in combination, to gauge consumer engagement with the promotion. Promotions with low consumer engagement may be discontinued, until only optimally performing promotions are remaining.

A method, apparatus, and computer program product are disclosed to improve the process of generating promotions. The method includes identifying a promotion structure for approval, the promotion structure defining a promotion to be displayed via a promotion and marketing service and determining whether the promotion structure satisfies automatic approval requirements, the automatic approval requirements including one or more parameters relating to the promotion structure. The method further includes in an instance in which the promotion structure satisfies the automatic approval requirements, automatically approving the promotion structure for display via the promotion and marketing service, and in an instance in which the promotion structure does not satisfy the automatic approval requirements, indicating that the promotion structure cannot be automatically approved. A corresponding apparatus and computer program product are also provided.

A method for detecting a user's outlier days uses data corresponding to features of the user acquired over multiple days by sensors on the user's electronic device. The data acquired for each day and feature is labeled as regular or irregular by applying N labeling approaches. One of the N labeling approaches compares the data for each feature with how values of previously acquired data for corresponding features are distributed. N labels are generated for the data for each feature and day. The machine learning classification model is trained using one of the N labels for each of the N labeling approaches. An optimal labeling approach is selected from among the N labeling approaches for each feature using the machine learning classification model. For each feature, the method determines whether each of the days is an outlier day for the user using the labels obtained with the optimal labeling approach.

Methods and apparatus for generating intelligent offers with base prices are provided. In one embodiment, a promotion generator receives a current product base price, and also receives or calculates a remaining promotional program budget, a remaining promotional program duration, and a minimum discounted price for the product using the current product base price and any available previous base price data for the promoted product, creating or updating a predictive model of future product base prices.

Embodiments of the present specification provide methods for performing marketing cost control by using a deep reinforcement learning system. One method includes the following: determining a cost of a marketing activity; determining a reward score of reinforcement learning that is negatively correlated with the cost; and returning the reward score to a smart agent of a deep reinforcement learning system, for the smart agent to update a marketing strategy, wherein the smart agent is configured to determine a marketing activity based on the marketing strategy and status of an execution environment of the deep reinforcement learning system.

Apparatuses and methods of controlling scheduling of displays presented in response to data indicative of user inputs from user terminals in a computerised system are disclosed. A performance metric is determined for a response by a data processing apparatus configured to respond to user terminals, the response being provided in accordance with a strategy of scheduling displays when responding to data indicative of at least one user input. A response performance score is computed based on the determined performance metric and a reference metric representative of a preferred result when responding data indicative of user inputs. It can then be determined, based on the response performance score, whether the strategy of scheduling displays when responding data indicative of user inputs needs a change.