An automatic system facilitates selection of media properties on which to display an advertisement, responsive to a profile collected on a first media property, where a behavioral-targeting company calculates expected profit for an ad correlated with the profile and arranges for the visitor to be tagged with a tag readable by the selected media property. The profit can be calculated by deducting, from the revenues that are expected to be generated from an ad delivered based on the collected profile, at least the price of ad space at a media property where the BT company might like to deliver ads to the profiled visitor. When the calculated profit is positive (i.e., not a loss), the BT company arranges for the visitor to be tagged with a tag readable by the selected media property through which the BT company expects to profit.

Computer implemented sales prediction system collects data relating to events of visitors showing an interest in a client company from plural data sources, an organization module which organizes collected data into different event types and separates collected event counts in each event type between non-recent and recent events occurring within a predetermined time period, a first processing module which periodically calculates weighting for each event type based on recent and non-recent events for the event type compared to totals for other selected event types, a second processing module which periodically calculates sales prediction scores for each visitor and companies with which visitors are associated based on accumulated event data and weighting, and a reporting and data extract module which is configured to detect variation in sales prediction scores over time to identify spikes which can predict upcoming sales and to provide predicted sales information and leads to the client company.

A method includes receiving data indicative of content to be published by a publisher and generating output text data based on comparing text data output by different text recognition operations on the received data. Another method includes extracting one or more text items and one or more images from the received data, determining that the content is associated with a first entity, and generating a directory webpage that includes the one or more text items and the one or more images. The directory webpage is associated with the first entity and is hosted in a subdomain of a domain associated with the publisher. A particular text item of the one or more text items, a particular image of the one or more images, or both, is associated with offer information.

Methods and systems for attributing contributions to digital marketing campaigns in achieving an action are described. In one or more implementations, first, second, and third order probabilities of a user taking the action are computed for each of a plurality of campaigns of a campaign path. Based on the probabilities, contributions are attributed to the campaigns of the campaign path in achieving the action.

Online entities oftentimes desire to ascertain information about their audience members. To determine information about audience members and their activities, online transactions including information about transactions performed by audience members are collected. One or more audience analysis processes are applied to the online transactions to determine the collection of online transactions performed by a given audience member. With an accurate assignment of online transaction to the audience member, the audience member and associated transactions may be classified as a legitimate or illegitimate.

Television is the largest advertising category in the United States with over 65 billion spent by advertisers per year. A variety of different targeting algorithms are compared, ranging from the traditional age-gender targeting methods employed based on Nielsen ratings, to new approaches that attempt to target high probability buyers using Set Top Box data. The performance of these different algorithms on a real television campaign is shown, and the advantages and limitations of each method are discussed. In contrast to other theoretical work, all methods presented herein are compatible with targeting the existing 115 million Television households in the United States and are implementable on current television delivery systems.

The invention addresses the problem of building self-service systems for digital-content monetization that may attract and grow advertising supply and demand mainly through their internal programmatic means. The invention reduces the need for external propulsion through a costly sales force and business-development interventions, and serves as a mechanism for boosting user acquisition and monetization of the system itself. The invention employs three types of store fronts with special insights designed to facilitate the attainment of user, publisher and advertiser objectives and to increase the likelihood of favorable events for the system's automated propulsion. The propulsion method exploits asymmetry in the relationships between advertisers, publishers, and users in order to grow supply and demand synchronously while employing an advertising model based on digital-content sponsorship in the form of programmatic-direct advertising.

A device and method, as disclosed herein, are operable to receive reference data during an in-process period that occurs while an advertising campaign is implemented based on purchase data. The reference data includes first reference data arranged in accordance with a first data organization. The reference data also includes second reference data arranged in accordance with a second data organization that differs from the first data organization. The purchase data includes an actual rate related to one or more ad placements. During the in-process period, with respect to the at least one ad placements, the device and method are operable to determine a plurality of metrics related to the one or more ad placement. The metrics depend at least partially on the reference data. Also, during the in-process period, the device and method are operable to determine a target rate related to the one or more ad placements. The target rate depends at least partially on a plurality of the metrics. The device and method are operable to cause an output device to indicate information based on a difference between the target rate and the actual rate related to the one or more ad placements.

Disclosed examples determine a unique audience exposed to media while reducing memory resources of a computing device. Example instructions program programmable circuitry to log a plurality of impressions corresponding to media accessed at client devices; generate a first value based on a count of the impressions and a count of users of a database proprietor that accessed the media; generate a second value based on the first value and a count of demographic impressions logged by the database proprietor; and determine a unique audience size based on the second value.

A computer-implemented method for efficiently estimating the number of unique elements in a collection of elements comprises generating, via hash logic, hash values associated with the elements. The hash values specify bit positions within an array of bits. Hash values output from the hash logic conform to a geometric distribution such that bit positions of the array of bits corresponding to lower orders bits are more likely to be generated than bit positions corresponding to higher-order bits. Bits of the array of bits corresponding to the bit positions are set. The number of bits of the array of bits that are set is counted. Estimation logic estimates the number of unique elements of the collection of elements as a function of the number of bits of the array of bits that are set.