Systems, methods, and other embodiments associated with predicting customer behavior are described. The method can include identifying a group comprising customers who satisfy a defined criterion, and receiving input that identifies a factor that influences a decision by the customers to purchase a product. A likelihood that the factor will induce the customers in the group to purchase the product is generated. A customer influence on the generated likelihood is estimated independently of data expressly identifying relationships between the customers in the group. The likelihood is modified by combining the likelihood and the customer influence according to a predictive model, and one or more of the customers eligible for a promotional offer related to the product is identified based, at least in part, on the modified likelihood. Transmission of the promotional offer is controlled to transmit the promotional offer to the identified customers in the group.

A plurality of different hosted services each include enabling logic that enables a set of actions. Usage data for a plurality of different tenants is accessed and actions are grouped into features based upon underlying enabling logic. A correlation score between features is identified based on tenant usage data for those features. A tenant under analysis is selected and usage data for the tenant under analysis is used to identify related features that the tenant under analysis is not using, based upon the correlation scores for the features. An output system is controlled to surface the related features for the tenant under analysis.

There is provided a method of calculating a set of sequential adjustments, comprising: designating content variations to clusters of target entities that are compliant with defined target entity feature(s) according to a set of decision rule(s), calculating performance outcome(s) based on an analysis of data collected from execution of the decision rule(s), calculating sequential adjustment(s) of the decision rule(s), according to an analysis of a predicted performance outcome calculated based on assigning content variation(s) to respective target entities according to an adjusted set of decision rules, and wherein each sequential adjustment includes alternative decision rule(s) designating content variation(s) to a respective cluster of target entities that are compliant with entity feature(s), and presenting the sequential adjustment(s) including the target entity feature(s) with which the cluster of target entities is compliant, and alternative decision rule(s) including content variation(s) designated to respective clusters of target entities.

In one embodiment, a method of transmitting streaming media and advertisements to viewers at a plurality of viewer nodes is disclosed in which a plurality of viewer groups are created. Each viewer node is assigned to one of the plurality of viewer groups, wherein the assigning includes creating an advertising group map disclosing an advertising group to which each viewer belongs and transmitting the advertising group map to each viewer node. At the head end, at least one media stream is received including media content. A plurality of presentation streams is formed, each presentation channel corresponding to one of the viewer groups, by replicating the at least one media stream, each presentation channel including the media content and advertisements, wherein the advertisements replace previously scheduled advertisements. Each of the presentation channels is transmitted to at least one viewer node in said viewer group corresponding to said presentation channel.

A system and method is provided for adding at least one advertisement to a personal communication and providing additional communication data to a recipient that interacts with the advertisement. A sender network device communicates with an advertising application operating on a Web site to generate a personal communication containing at least one advertisement, where the at least one advertisement is selected from a palette of advertisements. In one embodiment of the present invention, the sender has control over advertisements that are displayed together with the personal communication by allowing the sender to delete (or remove) an advertisement from either the at least one advertisement or the palette of advertisements. If a displayed advertisement is interactive, and the advertisement is interacted with, the advertising application will provide the recipient with additional communication data in a format that can be understood by the recipient network device.

Performance-based digital content delivery in a digital medium environment is described. Initially, different items of a collection of digital content are delivered to a substantially equal number of users. The collection is then iteratively tested to identify which content item achieves a desired action (e.g., conversion) at a highest rate. During the iterative test, data describing user interaction with the delivered content is collected. Based on the collected data, measures of achievement are determined for the different content items. Measures of statistical guarantee are also computed that indicate an estimated accuracy of the achievement measures. Responsive to determining that a condition for ending the test has not yet occurred, an optimized allocation is computed for delivery of the content by applying one of multiple allocation optimization techniques. The particular technique applied is based on the condition for ending the test and a type of statistical guarantee associated with the test.

Systems, methods, and non-transitory computer readable media can determine qualitative ratings associated with a plurality of advertisements based on a machine learning model. One or more clusters of the plurality of advertisements can be generated based on representations of the plurality of advertisements. One or more advertisements visually similar to an advertisement can be identified based at least in part on a cluster of the one or more clusters and qualitative ratings of advertisements in the cluster.

Techniques for leveraging performance data to dynamically selecting content item-format pairs are provided. In response to receiving a request, a content campaign is selected and feature values associated with the request are identified. Based on the feature values, performance values are identified, where each performance value is associated with a different content item-format pair of multiple content item-format pairs. Based on the performance values, a particular content item-format pair is selected. The selected pair may not be associated with the highest performance value. The particular content item of the selected pair is transmitted over a computer network and presented on a computing device according to the format of the selected pair.

An online system receives product data from a third party system describing characteristics of a product being offered by a third party system. The online system compares a price of the product being offered by the third party system to prices for the product being offered by other systems. The online system determines a competitiveness value for the product offered by the third party system relative to the other systems. Accordingly, when the online system identifies an opportunity to present a content item to a user, the online system retrieves candidate content items, determines a score for each candidate content item, and adjusts the score of the content item offered by the third party based on the competitiveness value for the product.

A system and method is provided for adding at least one advertisement to a personal communication and providing additional communication data to a recipient that interacts with the advertisement. A sender network device communicates with an advertising application operating on a Web site to generate a personal communication containing at least one advertisement, where the at least one advertisement is selected from a palette of advertisements. In one embodiment of the present invention, the sender has control over advertisements that are displayed together with the personal communication by allowing the sender to delete (or remove) an advertisement from either the at least one advertisement or the palette of advertisements. If a displayed advertisement is interactive, and the advertisement is interacted with, the advertising application will provide the recipient with additional communication data in a format that can be understood by the recipient network device.