Abstract: Systems and methods are provided for delivering invitational content based on a prediction of the intent of a user. In particular, partial action sequences are identified in a journal of events associated with the user. Thereafter, the partial sequences are analyzed and scored based on their degree of proximity to completion. Based on this scoring, a queue of invitational content can then be generated, where the scoring can be used to select and order the invitational content for the user. In some configurations, the information in the journal can be used to determine future time intervals at which sequences will be completed by the user. Consequently, a queue can be adjusted to provide delivery of appropriate invitational content at these future time intervals.

Abstract: Systems and methods are provided for selecting invitational content for users based on their short-term and their long-term features. In operation, responsive to a request from a user terminal for a content package a journal of events associated with a user. Thereafter, short-term and long-term features in the journal are identified and tagged with pre-defined tags indicating a type of content associated with the patterns. The tags are then used to select invitational content by selecting content based on tags for the identified short-term features associated with a threshold level of activity or tags for the identified long-term features.

Abstract: Segments used to select content to be targeted to a user are recursively refined based on continuously derived user characteristics. Based on information gathered from new requests for targeted content and/or user interaction with previously delivered content the user is assigned to one or additional targeted segments. The targeted segments can be used to select content to be delivered to the user based on the user's assignment to the targeted segments. Accordingly, each user is grouped into one or more targeted segments and based on the user's inclusion in those segments, requests for targeted content can be served to the user.

Abstract: Systems and methods are provided for selecting invitational content for users based on their short-term and their long-term features. In operation, responsive to a request from a user terminal for a content package a journal of events associated with a user. Thereafter, short-term and long-term features in the journal are identified and tagged with pre-defined tags indicating a type of content associated with the patterns. The tags are then used to select invitational content by selecting content based on tags for the identified short-term features associated with a threshold level of activity or tags for the identified long-term features.

Abstract: Systems and methods are provided for audience targeting based on a performance history of invitational content from secondary content providers, such as advertisements. In operation, responsive to request from a user for content package, a queue of available invitational content is retrieved. Thereafter, based at least on a performance history of the available invitational content in the queue, a context of the primary content, and a performance history of invitational content previously presented to other users, the queue can be at least partially reordered to provide an adjusted queue. The invitational content for the content package can then be selected based on the adjusted queue.

Abstract: Systems and methods are provided for delivering invitational content based on a prediction of the intent of a user. In particular, partial action sequences are identified in a journal of events associated with the user. Thereafter, the partial sequences are analyzed and scored based on their degree of proximity to completion. Based on this scoring, a queue of invitational content can then be generated, where the scoring can be used to select and order the invitational content for the user. In some configurations, the information in the journal can be used to determine future time intervals at which sequences will be completed by the user. Consequently, a queue can be adjusted to provide delivery of appropriate invitational content at these future time intervals.

Abstract: The present technology is directed to improving the conversion rate of invitational content that is provided to the user of an interactive, content-receiving-and-displaying device. The content of a large number of primary-content sources is analyzed and keyword and/or other context-providing information is extracted from the primary-content sources. The keyword and/or other context-providing information is used to index the primary-content sources into an index according to a hierarchical taxonomy; the hierarchical taxonometric index is used to identify primary-content sources with which a given item of invitational content correlates; and the given item of invitational content is delivered to a user in response to the user accessing a primary-content source with which the given item of invitational content correlates.

Abstract: Systems and methods are provided for booking and managing electronic campaigns. In particular, electronic campaigns are booked by obtaining a correlation between campaign input parameters for the campaign, campaign output characteristics for the campaign, and network output characteristics of network elements affected or impacted by the campaign. The correlation can then be used to identify sets of values for the input parameters that result in the various output characteristics meeting some criteria and one of the sets can thereafter be used to book an electronic campaign. At a later time, if the actual values for the various output parameters fail to meet corresponding criteria, the correlation can be updated to identify and select a new set of campaign input parameter values for the electronic campaign.

Abstract: Systems and methods are provided for selecting invitational content for users based on their short-term and their long-term features. In operation, responsive to a request from a user terminal for a content package a journal of events associated with a user. Thereafter, short-term and long-term features in the journal are identified and tagged with pre-defined tags indicating a type of content associated with the patterns. The tags are then used to select invitational content by selecting content based on tags for the identified short-term features associated with a threshold level of activity or tags for the identified long-term features.

Abstract: The process of constructing a successful targeted content campaign can be time consuming and error prone. By having access to performance data, adjustments can be made, such as to the tasks performed by the content delivery system, the available content, or the campaign parameters, to improve performance. As the delivery system performs its tasks, it can collect a variety of information regarding the activities within the delivery system. Based on the collected information, the delivery system can obtain performance data for the various campaigns. The delivery system can then analyze the performance data to identify any campaigns that have failed to meet the specified performance criteria. When a non-conforming campaign is detected, the delivery system can attempt to determine the cause of the non-conformance and send an alert to the appropriate entity. Additionally, in some cases, the delivery system can include in the alert suggestions for improving the campaign performance.

Abstract: Invitational content can be served to a user taking into account temporal considerations. By using temporal considerations, such as dayparts having a relationship to the content or the user, the content delivery system can better associate content to users to increase the relevance of the content to the user, to increase the user's interest in the content, and to increase the performance of the content delivery system as judged by the meeting of system objectives.

Abstract: The presently described technology provides a mechanism for allowing custom targeted segments to be defined by parties outside of a content delivery system. Segments include collections of users grouped together based on common characteristics wherein targeted content is provided to a user based on her assignment to a segment. The present technology allows a content provider, as an example, to define a custom segment, thereby creating a grouping of users suited to receive the content provider's content. In some embodiments, a user interface is provided to the content provider, which includes all available characteristics, and value ranges corresponding to the characteristics. The content provider selects from among the characteristics and values corresponding to the characteristics to create a definition of a custom segment.

Abstract: The present technology derives unknown user characteristics from known user characteristics. Unknown characteristics can be inferred from products purchased by a user; by comparing two similar users and inputing characteristics known about one user to another user with unknown characteristics; by inferring characteristics using classifying algorithms to infer additional user characteristics from a collection of other known data about a user. The inferred characteristics can further be associated with a confidence score which is an indication of the likelihood that the inferred value is the correct value for a user.

Abstract: Segments used to select content to be targeted to a user are recursively refined based on continuously derived user characteristics. Based on information gathered from new requests for targeted content and/or user interaction with previously delivered content the user is assigned to one or additional candidate segments. The candidate segments can be used to select content to be delivered to the user based on the user's assignment to the targeted segments. Accordingly, each user is grouped into one or more targeted segments and based on the user's inclusion in those segments, requests for targeted content can be served to the user.

Abstract: The present technology prioritizes or ranks segments based on the content provider's or content delivery system's goals or priorities. The content delivery system can monitor its performance in meeting any known goals, and should the content delivery system recognize that its progress towards meeting a goal is not satisfactory, the content delivery system can prioritize some segments over others to meet one or more goals. Since prioritizing a selection of segments can impact other system and content provider goals, the system can also be provided with a performance predictor that can run a series of prediction models to predict the optimum prioritization of segments to result in the best performance of the system.

Abstract: The present technology analyzes a user's behavior to assign a user to targeted segments. The segments to which the user is assigned can be a reflection of a user's context with respect to potential targeted content. While a user can be assigned to many different segments, the user is likely to be most interested in content that she is presently interested in. Accordingly, the system can also prioritize or rank or order segments based on the user's present context. Content is then provided to the user on the basis of the segments to which the user belongs and the priority of segments.

Abstract: The present technology allows reliable and accurate tracking of conversions of invitational content by storing token identifying items of invitational content presented to the user within a cookie jar of a local occurrence of an online-store application. When a purchase or download is made from the online store, the cookies are sent to the online store, which can match the purchase or download with the tokens. Thus, conversions can be tracked as they are completed.

Abstract: Systems and methods are provided for audience targeting based on a performance history of invitational content from secondary content providers, such as advertisements. In operation, responsive to request from a user for content package, a queue of available invitational content is retrieved. Thereafter, based at least on a performance history of the available invitational content in the queue, a context of the primary content, and a performance history of invitational content previously presented to other users, the queue can be at least partially reordered to provide an adjusted queue. The invitational content for the content package can then be selected based on the adjusted queue.

Abstract: The present technology maintains a profile for each user known to a content delivery system and selectively excludes delivery of certain content to some users based on past performance. The user profile includes a listing of all completed conversion actions associated with the invitational content presented to the user. When presented with a request for invitational content, the system identifies the set of all possible invitational content for the given context. Based on the user profile, the system removes from the set all invitational content for which the user has completed the associated conversion action to create a user-specific set of invitational content. The system selects an invitational content from the user-specific set of invitational content to include in the content package presented to the user.

Abstract: A present technology intelligently retargets invitational content to a user by maintaining a user profile that includes data descriptive of the user's interaction with invitational content previously presented to the user and making decisions regarding retargeting based on an analysis of the user profile. The information in the user profile is not limited to whether or not the user completed a conversion action associated with invitational content presented. Rather, the profile is expanded to include such information as where on the conversion continuum the user abandoned the process and details of how the invitational content was presented to the user, e.g. colors used, situation, and message. When presented with a request for invitational content, the system uses the profile information to influence which content is selected and how it is presented to the user.