Multi-computing device network based cross-device conversion determination is described. A content selection computer server can identify cross-device conversions. A first computing device accesses third-party content via a first computer network connection. A second computing device accesses a webpage of the third-party content provider via a second computer network connection. The first and devices can be logged into a same online account. The content selection computer server can obtain, via a content tag that includes a script that executes on a webpage that includes the third-party content, data indicating that the first computing device accessed the third-party content. The selection computer server determines the conversion from the content tag and the second computing device having accessed the webpage. Based on a percentage of first and second sets of computing devices that have logged into common respective online accounts, the content selection computer server extrapolates an estimated number of cross-device conversions.

The present disclosure provides methods and computer systems for displaying or projecting media on a remote visual curvilinear display. In a computer system, a computer server may be in network communication with an electronic device of a user. One or more parameters associated with the user may be determined. The media may be selected for display or projection by the remote visual curvilinear display device of the user. The media may be selected based on the one or more parameters associated with the user. The media may be directed from the computer server to the electronic device for display or projection on the remote visual curvilinear display. An item of value of the user may be received on the computer server in exchange for the media.

Font or format-based heuristic extraction of data structures are described. A data structure storage entity is accessed. A heuristic extraction technique comprising a font or format-based policy is used to parse the data structure and extract data from the data structure. Content selection criteria is determined from the data extracted from the data structure using the parsing technique. Online content items are generated with the determined content selection criteria. An online content item is selected responsive to location information received via a global positioning component of a computing device. The computing device receives, via a network, the selected online content item and is instructed to render the selected online content item.

An online system determines an estimated conversion rate for sponsored content items placed on content publishers and on the online system. The estimated conversion rate can be determined by a machine learning model trained using data describing content campaigns, content publishers, and online system users. This data is collected by the online system from content publishers and/or content campaigns that report conversion rates to the online system. By determining a ratio of estimated conversion rates with third party content on the content publisher against those on the online system, the online system can determine a publisher quality score for that content publisher. The online system uses the publisher quality score to normalize third party value contributions toward placing sponsored content on content publishers and the online system. Thus, disparities in the intrinsic value across publishers are diminished as third party value contributions are normalized based on the publisher conversion rates.

Web marketing channel correlation information for multiple web access sessions is captured using a web sales-capable server. The web marketing channel correlation information includes, for each web access session, a session-originating web marketing channel identifier of a marketing channel that originated the web access session, and at least one cross-session correlation identifier usable to correlate sets of web access sessions and usable to correlate the sets of web access sessions with orders. In association with an order placed by a consumer using the web sales-capable server, an accumulated statistical sales contribution of each marketing channel that originated a correlated set of web access sessions that are correlated with the order is calculated based upon the captured marketing channel correlation information. The accumulated statistical sales contribution of each marketing channel is calculated using a statistically-accumulated marketing channel attribution metric associated with each correlated marketing channel.

Web marketing channel correlation information for multiple web access sessions is captured using a web sales-capable server. The web marketing channel correlation information includes, for each web access session, a session-originating web marketing channel identifier of a marketing channel that originated the web access session, and at least one cross-session correlation identifier usable to correlate sets of web access sessions and usable to correlate the sets of web access sessions with orders. In association with an order placed by a consumer using the web sales-capable server, an accumulated statistical sales contribution of each marketing channel that originated a correlated set of web access sessions that are correlated with the order is calculated based upon the captured marketing channel correlation information. The accumulated statistical sales contribution of each marketing channel is calculated using a statistically-accumulated marketing channel attribution metric associated with each correlated marketing channel.

Embodiments disclosed herein relate to systems and methods for validating adcopy instructions. A method may include generating, by a computer including one or more processors, media content. The method may also include identifying, by the computer, a destination server to receive playback statistics associated with playback of the media content. Furthermore, the method may include determining, by the computer, a callback address identifier associated with the destination server. Additionally, the method may include encoding, by the computer, the callback address identifier within the media content and transmitting, by the computer, the media content to a user device for playback.

In general, embodiments of the present invention provide systems, methods and computer readable media for data record compression using graph-based techniques.

Systems and methods of evaluating information in a computer network environment are provided. A data processing system can obtain or receive a content placement criterion, such as a keyword, associated with a content item and can determine a quality metric of the content placement criterion. The data processing system can identify a candidate content placement criterion and expand placement criteria associated with the content item to include the content placement criterion and the candidate content placement criterion based at least in part on an evaluation of the quality metric of the content placement criterion. The data processing system can expand placement criteria based in part on a throttling parameter. The data processing system can identify a correlation between a document and the placement criteria to identify appropriate content items for the document.

Disclosed are a system and a method enabling E-Commerce transactions without redirecting a user's computer from one electronic publishing page to another electronic publishing page.