A computer implemented method, apparatus, and computer usable program code for customizing digital media marketing messages. In one embodiment, external data is received from a set of detectors located externally to a retail facility to form external data. The external data is processed to form dynamic data. The set of dynamic data is analyzed using a data model to identify personalized marketing message criteria for the customer. A customized marketing message for the customer is generated using the personalized marketing message criteria. The customized marketing message is delivered to a display device associated with the customer for display.

A computerized information and display apparatus useful for providing information to a user via a display. In one embodiment, the apparatus comprises a processor apparatus, touch screen input and display device, and speech input apparatus, and at least one computer program configured to run on the processor apparatus, the at least one program being configured to enable an user to intuitively operate the apparatus to rapidly converge on a desired organization or entity which they wish to locate, via speech input of only a name or a part of a name. The information and display apparatus is particularly useful in time-pressured mobile transport vehicle environments, and when the user is unfamiliar with the operation of the apparatus.

The cardinality of an audience logical expression is estimated in real time based on Hyperloglog data structures. In embodiments, an apparatus includes a communication module to receive a query for cardinality estimation associated with an audience logical expression. Further, the apparatus includes a conversion module to convert the audience logical expression into an equivalent expression based on selected Hyperloglog data structures, and an estimation module estimates the cardinality associated with the audience logical expression based on one or more addition or subtraction operations with the respective cardinality associated with the selected Hyperloglog data structures.

Disclosed herein are systems, methods, and devices for generating efficacy metrics. Systems may include a data object aggregator configured to receive a plurality of advertisement data objects characterizing online advertising content associated with at least one online advertisement campaign. Systems may also include an efficacy metric generator configured to generate a plurality of efficacy metrics characterizing an estimate of a probability of at least some of the plurality of advertisement data objects interacting with a target audience, where the generating is based on one or more properties of the plurality of advertisement data objects. Systems may further include a report generator configured to generate at least one report based on the plurality of efficacy metrics.

Various technologies described herein pertain to prefetching content units. A prefetch request is transmitted to a server from a client device. The prefetch request includes data indicative of probabilities of slots for content units being available during an upcoming time period. The probabilities can be based on likely interaction with application(s) executed by the client device during the upcoming time period. Prefetched content units assigned to the client device for the upcoming time period can be received from the server responsive to the prefetch request. One or more of the prefetched content units can be served for display on a display screen of the client device during execution the application(s). Further, statuses of the prefetched content units can be monitored, and information that specifies a subset of the prefetched content units that are unlikely to be displayed on the display screen prior to corresponding deadlines for expiration can be transmitted.

Various technologies described herein pertain to allocating content units to client devices. Content units can be requested from an exchange by a server. The content units can be received by the server from the exchange, where the content units each has a corresponding deadline for expiration. Further, an indication of a penalty can be transmitted to the exchange if one of the content units is not displayed by one or more client devices upon expiration of the corresponding deadline.

The present disclosure relates to a computer system configured establish and utilize a database for online ad realization prediction in an ad display platform associated with N parties, wherein N is a positive integral greater than 1. The computer system is configured obtain a party hierarchy for each of the N parties including a plurality of features of the party; select a target ad display event including N features, each of the N features corresponding to a node in a party hierarchy; obtain a prior probability reflecting an unconditional probability of ad realization occurrence at the target ad display event among all possible ad display events; for each of the N features: determine a marginal prior probability by decomposing components associated with the other N1 features from the prior probability; determine a marginal posterior probability based on the marginal prior probability; and save the marginal posterior probability in the corresponding node of the party hierarchy.

The present invention generally teaches systems and methods for creating appliance signatures based upon whole house composite load profiles. Methods may includes steps such as identifying primitive elements including transients and absolute steady state levels; clustering the primitive elements along multiple dimensions to form impulses; combining impulses to form simple bundles; combining simple bundles with each other or impulses to form complex bundles; and determining specific appliance signatures that substantially match the complex bundles. Methods may also include steps such as determining transitions within the whole house composite load profile; determining household specific appliance state machines for each appliance in the household; and disaggregating the whole house composite load profile into individual appliance energy loads by assigning the determined transitions to the determined household specific appliance state machines.

A computer-implemented method includes identifying a first set of members on a social network, each member of the first set of members includes a class value comprising one of a positive member and a negative member, each positive member is associated with a target offering, determining a skillset of each member of the first set of members, training a first model based on the class value and skillset of each member of the first set of members, the first model configured to generate at least one of a classification value and a prospect score for a prospect member based on a prospect member skillset, computing a prospect score for the prospect member using the first model and the prospect member skillset, and providing the at least one of a classification value and a prospect score for use in evaluating the prospect member in relation to the target offering.

A transaction account provider may obtain transaction information from consumer transactions and information from a consumer browsing a transaction account provider website, collectively first-party data. A web server may obtain second-party data from a consumer's use of a merchant website. Additional third-party data may be purchased from a third-party data source. An ad server may use the first-party data, the second-party data, and the third-party data to select a relevant personalized banner ad to be displayed to the consumer.