An embodiment may involve receiving, from one or more server devices, representations of past amounts spent on paid search engine listings for a web site and representations of paid search conversions involving the web site that are attributable to the paid search engine listings. The embodiment may also involve receiving representations of past amounts spent on the display promotions for the web site and representations of display conversions involving the web site. The embodiment may also involve receiving a request for a graphical representation of the cross-channel performance of the web site with respect to conversions. In response to receiving the request for the graphical representation of the cross-channel performance of the web site, the computing system may transmit the graphical representation of the cross-channel performance of the web site.

Method and systems are disclosed for distribution of candidate information to a recruiter list. An example apparatus includes a candidate manager to retrieve, via a processor, a first keyword provided by a candidate during a session of the candidate on an employment website. The apparatus includes a recruiter-candidate comparator to query, in real time during the session, a database including bids for candidates. The recruiter-candidate comparator is to retrieve, in response to identifying that at least one of the bids for candidates includes the first keyword, one or more of the bids for candidates from the database that include the first keyword and determine a recruiter list to include at least one recruiter of the one or more bids for candidates that include the first keyword. The apparatus includes a recruiter manager to distribute, in real time during the session, candidate information of the candidate to the recruiter list.

Methods and computing apparatus for retrieving records relating to content placement events and records relating to user interaction events. A set of enriched training feature vectors is computed from raw feature values, and used with interaction event tags to train a machine learning model. Information is received relating to an online content placement slot and information is received relating to a user to whom content within the online content placement slot will be displayed. An enriched estimation feature vector is computed based upon a content item selected for placement within the online content placement slot, the information relating to the user, and the information relating to the online content placement slot. A machine learning model is executed to determine an estimate of likelihood of the user interacting with the selected content item, based upon the enriched estimation feature vector.

A hierarchical feature tree is generated. Each child node's feature is more specific than its respective parent node's feature. A behavioral model comprising features of the feature tree is created and used in the operation of an advertising campaign. A degraded model feature is detected at the discovery system by comparing a performance metric of a model feature from two different time windows. The discovery system matches a node of the feature tree with the degraded feature and selects a prospective model feature from a family node. An estimated performance metric for the prospective model feature is determined and the results are used to decide if the model should be updated to include the prospective model feature. The campaign can be operated with the automatically updated model.

Header bidding systems and methods increase a number of advertisers that can place bids for an advertising impression while maintaining low latency in loading of the webpage, while still permitting control for reporting and review of inappropriate advertising content. Even though advertising content may be received from a plurality of disparate advertising sources, information identifying the source of each advertisement is maintained such that when an advertisement is reported as inappropriate, information regarding the advertisement and the source of the advertisement is gathered and delivered to a review system, such that when advertisements are in fact deemed inappropriate, the correct advertiser can be notified and future display of the inappropriate advertisement blocked.

A media presentation and distribution system includes a verification server that handles dynamic verification of playback of media assets on a client device. The client device receives an asset stream of media assets that comprises one or more tags embedded in the media assets. The client device detects an asset identifier associated with each of the media assets during playback of each media asset on the client device, based on identification of a tag of the one or more tags. The verification server verifies the playback of the media assets on the client device based on received support information from the client device. The playback of the media assets are verified to satisfy defined asset delivery criteria and to identify and debug a deviation or one or more errors with the playback of the media assets.

A media presentation and distribution system communicatively coupled to a client device, which handles enablement of a client-side dynamic presentation of at least one non-programming media asset along with programming media content. The client device receives a first media stream of the programming media content in response to a request, associated with at least one user preference for the programming media content, to the media presentation and distribution system. The client device identifies at least one tag in the programming media content and transmits at least one event opportunity point for selection to the media presentation distribution system. Based on the selection, the client device modifies a display view of the client device for a defined duration, and presents the at least one non-programming media asset, from a second media stream for the defined duration, concurrently with the programming media content over the modified display view of the client device.

A method for performing an agricultural service in which a server platform communicates with a user and with service providers. The server platform has a field file of field information about at least one agricultural field associated with the user. The server platform generates a service order based on the field information and on service instructions received from the user to perform an agricultural service with an order profile. The server platform generates service bids with a bid profile from service provider data of service providers. The server platform compares the order profile with the bid profiles, and suggests to the user one or more bids fitting the service order based on the degree of matching between the order profile and bid profiles. The server platform commissions the service provider of the selected bid to perform the service based on the user's selection of one of the service bids.

A system, method, and computer-readable medium are disclosed for performing a cross platform reward exchange marketplace operation, comprising: creating a cross platform rewards account within a cross platform reward exchange marketplace; transferring a reward from a first entertainment system to the cross platform rewards account; placing the reward up for auction via the cross platform reward exchange marketplace; enabling monitoring of bids relating to the reward up for auction; accepting one of the plurality of bids relating to the reward up for auction; and, performing an exchange transaction via the cross platform reward exchange marketplace, the exchange transaction exchanging the reward up for auction and the one of the plurality of bids.

In general, embodiments of the invention relate to servicing fill request using ad networks and demand-side partners.