Apple Inc.

Lotame Solutions Inc.

Admobius, Inc.

Omar T Abdala

Dan Grigorovici

Eswar Priyadarshan

Kenley Sun

Jayasurya S Vadrevu

Ravikiran Chittari

Prasenjit Mukherjee

Hao D Duong

Hao Duong

Eswar Priyadershan

One exemplary system can determine a digital footprint for a user. The system can determine a first transmission pattern in which first content was transmitted to a first user device based at least in part on the digital footprint. The system can determine training data that includes a relationship between (i) one or more characteristics of the first content and (ii) the first transmission pattern. The system can then train a machine-learning-model using the training data to enable the machine-learning-model to predict a second transmission pattern in which to transmit second content that is different from the first content. The system can provide the second content as input to the machine-learning-model to obtain the second transmission pattern as output from the machine-learning-model. The system can cause the second content to be transmitted to the first user device in accordance with the second transmission pattern, which may conserve computing resources.

Managing data transmissions based on a user's digital footprint

The determination of a unique user is discussed in response to receiving a dataset comprising multiple user identifiers (IDs). In some cases the user IDs may be of a different type. User IDs may be compared directly to determine whether they correspond to a unique user. Network transactions and attributes associated with those network transactions may be compared to determine a probability of whether two user IDs correspond to a unique user. Network transactions and attributes associated with those network transactions may also be compared to determine that two user IDs do not correspond to a unique user.

Cookieless management translation and resolving of multiple device identities for multiple networks

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.

Selection and delivery of invitational content based on prediction of user interest

Systems and methods for planning and booking advertising campaigns are provided. In operation, a booking engine generates a collection of proposed campaigns in response to a campaign request, where the each of the proposed campaigns corresponds to a scenario of atom availability. Such scenarios can account for possible or anticipated changes in the number and cost of atoms or any other changes of interest to the advertiser. The availability for the atoms in the campaign request can be projected using the past history and the known future unavailability of the atoms and is further modified to account for the variation in atom availability associated with each scenario. Thereafter, the booking engine can present the results for each scenario to the advertiser and allow him to select a campaign.

Forecasting and booking of inventory atoms in content delivery systems

Systems and methods for managing electronic content from multiple content providers in a dynamic environment are provided. In operation, an advertiser can plan and book an electronic advertisement campaign by providing a campaign request specifying a requested inventory slot of atoms in an inventory space and other associated data. Thereafter, a proposed campaign can be generated based on an estimated availability of the atoms and any performance criteria specified by the advertiser. Once the proposed campaign is accepted and booked, the proposed campaign can be managed along with other active campaigns. These active campaigns can be managed based on a relative priority of the campaigns and an estimated availability for the atoms in the inventory space.

Booking and management of inventory atoms in content delivery systems

Invitational content targeted to a particular behavior can be served to the user when the user is likely to reproduce a desired behavior. The user is classified into one or more spatial-temporal segments based on an analysis of the user's characteristics and the user's past behavior. When a request is made for an item of invitational content, a spatial-temporal segment is selected based on a substantial likelihood that the current context will lead to a repeat of the representative past behavior. An item of invitational content associated with the selected segment is then served to the user.

Location-intention context for content delivery

Systems and methods are provided for selecting content based on user interactions with content previously presented to a user but failing to generate a conversion. In operation, a content delivery system delivers a content package to a user terminal, where the content package includes a content designed to elicit a pre-defined response, such as a conversion. The user terminal then presents the content to a user and generates a journal of events occurring in response to the content package. The journal is then used to determine the proximity of the events in the journal to the pre-defined response. If the degree of proximity to the desired response is high, the user is likely prepared to complete the conversion and therefore a same or similar content can be selected for the user terminal. Otherwise, new content can be delivered to the user terminal.

Content delivery based on user terminal events

Systems and methods are provided for selecting contexts for new invitational content and invitational content for new contexts. In particular, a performance history of delivered invitational content in known contexts is combined with similarity measures for the delivered invitational content, with respect to a new invitational content, to generate a list of potential contexts for the new invitational content. Similarly, a performance history of in known contexts with delivered invitational content can combined with similarity measures for known contexts, with respect to a new context, to generate a list of potential content for the new context. Further, a combination of these methods can be used to pair new invitational content with new contexts.

Predicting content and context performance based on performance history of users

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.

Selection and delivery of invitational content based on prediction of user intent

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.

Network-based targeted content delivery based on queue adjustment factors calculated using the weighted combination of overall rank, context, and covariance scores for an invitational content item

Growing community of inventors

Cambridge, MA, United States of America

Omar T Abdala