Methods and systems are described for providing programmatic bidding of advertisement inventory. In one embodiment, an advertising system includes an ad bidding component or module of an ad server and a storage medium coupled to the ad server. The storage medium stores instructions including instructions of the ad bidding component or module. Processing logic is configured to execute the instructions to receive a bid campaign function call for an ad campaign from an advertising entity, determine objectives for the advertising entity including life time value (LTV) for users and return on investment (ROI) for the ad campaign, determine targeted users having characteristics appropriate for satisfying the objectives of the advertising entity, and autonomously determine a dynamic ad bid price parameter and associated group of targeted users that satisfy the objectives of the advertising entity based on having characteristics that satisfy at least three different parameters.

A system for receiving data associated with a mobile content is configured to calculate an expected value of the mobile content based at least in part on the data received, and determine a bid amount for a sponsorship of the mobile content based at least in part on the expected value.

Methods and systems for providing advertisements for inclusion in video content. In one embodiment, a video is formatted into a specific format for advertising purposes. The format describes a standard for advertisement placement opportunities within a video in which a client device may select advertisements for display during these opportunities.

Billing data associated with telecom products provided by a variety of vendors is captured, normalized, and processed to calculate true profit margins by invoice, by vendor, by geographic location, by end-customer, by circuit, or combinations of these. A bill may be received from the vendor, and associated with a specific vendor profile. The vendor profile may include a validation routine specific to the vendor. A plurality of telephone numbers associated with an end-customer may be extracted from the bill based on the vendor profile and stored on a storage device. A previous bill from the vendor may be accessed in response to receiving the bill from the vendor. End-customer profitability may be determined for a first time period based on data extracted from the received bill and displayed.

Various systems and methods for aggregating data from disparate sources to determine an optimal package of data items are disclosed. For example, the system described herein can obtain data items from various sources, aggregate and/or organize the data items into an optimal package based on various criteria, and present, via an interactive user interface, the optimal package. Furthermore, the interactive user interface may enable a user to adjust the criteria used to aggregate and/or organize the data items. The system may interactively re-aggregate and re-organize the data items using the adjusted criteria as the user interacts with the package via the user interface. The system and user interface may thus enable the user to optimize the packages of data items based on multiple factors quickly and efficiently.

Embodiments are disclosed for predicting target events occurrence for an advertisement campaign. A computing device according to some embodiments assigns a label to an advertisement as unlabeled, in response to a notification that a prerequisite event occurs for the advertisement. The device generates feature vectors based on data that relate to the advertisement. The device further trains a machine learning model using the feature vectors of the unlabeled advertisement based on a first term of an objective function, without waiting for a target event for the advertisement to occur. The first term depends on unlabeled advertisements. The device predicts a probability of a target event occurring for a new advertisement, by feeding data of the new advertisement to the trained machine learning model.

A method and system for placement of graphical objects on a page to optimize the occurrence of an event associated with such objects. The graphical objects might include, for instance, advertisements on a webpage, and the event would include a user clicking on that ad. The page includes positions for receipt of the object material. Data regarding the past performance of the objects is stored and updated as new data is received. A user requests a page from a server associated with system. The server uses the performance data to derive a prioritized arrangement of the objects on the page. The objects are arranged according to a calculation and returned to the user on the requested page.

A revenue share analysis module can determine individual session revenues for content items provided by content providers. The module can also determine total session content revenues for each of the content items according to the determined individual session revenues, and determine respective content values for each of the content items according to the determined total session revenues for each of the content items. It also may determine total session provider revenues for each of the content providers according to the determined total session revenues for each of the content items, and determine respective provider values for each of the content providers according to the determined total session revenues for each of the content providers. Also, it can determine revenue share offers according to the content values and/or the provider values.

Methods, systems, and apparatuses, including computer programs encoded on computer-readable media, for advertisement keyword scoring. A processing circuit receives a request for an advertisement to be provided to a user during a user session. The advertisement is to be provided alongside other content that is associated with a first plurality of keywords. A processing circuit identifies a plurality of advertisements based on the first plurality of keywords. Each of the plurality of advertisements are associated with a second plurality of keywords. The processing circuit calculates a keyword score for each of the second plurality of keywords for each of the plurality of advertisements. Based on the keyword score, one of the keywords for each of the plurality of the plurality of advertisements is selected. Based on a comparison of the selected keywords, the advertisement to be provided to the user is selected.

The present disclosure relates to systems, non-transitory computer-readable media, and methods to generate sketches for clearing-bid values and bid-success rates based on multi-dimensional targeting criteria for a digital-content campaign and dynamically determine predicted values for the digital-content campaign based on the sketches. To illustrate, the disclosed systems can use a running-average-tuple-sketch to generate tuple sketches of historical clearing-bid values and tuple sketches of historical bid-success-rates from historical auction data. Based on the tuple sketches, the disclosed systems can determine one or more of a predicted cost per quantity of impressions, a predicted number of impressions, or a predicted expenditure for the digital-content campaign—according to user-input targeting criteria and expenditure constraints.