In a method a web page hosting a tag script has a first area and a second area smaller than the first area. The first area contains a third area smaller than the first area. The third area is not positioned within the second area when the web page is loaded, and the third area contains a first ad content sourced from a first real-time ad bidding auction. Determining in real time via the tag script (a) whether the first ad content was loaded in the web page for a predefined time period, and (b) based on the other determining whether the third area has been scrolled into the second area as of or after the predefined time period has expired, and requesting a second real-time ad bidding auction for a second ad content to be input into the third area and replace the first ad content.

The disclosed systems and methods provide a novel framework that provides mechanisms for a Deep & Cross Network (DCN) framework that performs distilled deep prediction for personalized stream ranking on portal websites. The disclosed framework is scalable to satisfy the much more stringent latency and computational requirements required by current network operating environments. The disclosed framework is able to dynamically evaluate and leverage live traffic on network sites in order to provide, update and maintain current recommendations for users as they traverse to a portal and when they navigate within the portal. The disclosed framework implements a DCN model(s) that is capable of being compressed into a model size for a unified optimization within a live traffic environment by combining knowledge distillation and model compression techniques. The disclosed framework is built as a light-weight deep learning model that can be served in production and perform on par with large models.

Systems and methods for providing an advertisement marketplace where buyers and sellers can trade mediacast advertisement inventory programmatically at local, national, and/or worldwide levels. The marketplace system may include a seller-controlled marketplace system which connects sellers with buyers and offers revenue management tools for optimizing yields across direct and programmatic channels. The advertisement inventory is bought and sold as canonical inventory units which group similar but discrete advertisement slots together. The marketplace system may include a seller side platform (SSP) for sellers through which sellers can access demand across multiple sales channels and can make advertisement inventory available and accept or reject bids based on marketplace demand.

One or more computing devices, systems, and/or methods for implementing a model for serving exploration traffic are provided. An amount of spend by a content provider to provide content items of the content provider through a content serving platform to client devices of users is determined. A number of exploration impressions of users viewing exploration content items of the content provider over a timespan is determined. A return on exploration impression metric is determined for the content provider based upon a ratio of the amount of spend to the number of exploration impressions. The return on exploration metric is used to rank available exploration content items of content providers for serving exploration traffic.

Keyword bids determined from sparse data are described. Initially, a portfolio optimization platform identifies which keywords included in a portfolio of keywords are low-impression keywords. This platform trains a machine learning model to generate bids for the low-impression keywords with historical data from a search engine. In particular, the platform trains this machine learning model according to an algorithm suited for training with sparse amounts of data, e.g., a temporal difference learning algorithm. In contrast, the platform uses different models, trained according to different algorithms than the low-impression keyword model, to generate bids for keywords determined not to be low-impression keywords. Once the low-impression keyword model is trained offline, the platform deploys the model for use online to generate actual bids for the low-impression keywords and submits them to the search engine. The platform continues to update the low-impression keyword model while deployed according to the sparse-data algorithm.

The current invention relates to a computer-generated method for optimizing placement of advertising content across multiple different devices. The system can allocate advertising campaigns and plans to various inventory types based on the probability of accurate consumer matching. Consumer matching can be achieved by generation of look-alike models in a consumer's device graph to predict future consumption behavior. The system includes an interface through which an advertiser can access relevant information about inventory and success of a given placement.

Sponsored and organic pieces of content are displayed in accordance with a blending model that is used to first identify a pattern of slots to which to assign either sponsored or organic pieces of content. This blending model is applied to a combination of both sponsored and non-sponsored pieces of content being considered for display to a user. This pattern only determines the slot assignments. The actual ranking of the pieces of content, and more particularly the actual ranking of the organic pieces of content, is determined by an ordering other than the ranking determined by the blending model, such as by using the original ordering of the second list. The pieces of content are then displayed in the order of this actual ranking, but in the slots indicated as having been assigned to be either sponsored or organic in the pattern determined by the blending model.

The subject technology provides a targeted content curation and placement optimization system comprising a processor connected to a publication network, the publication network navigated by an online consumer seeking actionable content. An online demand side portal is accessible, via the publication network, to a content provider. An online supply side portal is accessible, via the network, to a publisher of content on the publication network. An integrated bidding exchange is communicatively coupled to the demand side portal and the supply side portal and presents user interfaces enabling receipt of bids from the content provider for placement of content by the publisher at a specified location or domain on the publication network. A geographic insights generator may generate geo-specific intender attributes that may be used to curate the targeted content and optimize one or more bidding parameters of the content provider.

A system that handles delivery of service(s) through a client device, includes an interactive service provider, a video service provider, and a client device. The interactive service provider inserts at least one of digital watermarks and digital fingerprints in non-programming media content. The video service provider transmits a media stream of the media content that includes programming media content and the non-programming media content. The client device detects at least one of the inserted digital watermarks and the digital fingerprints in the playback duration of the media content and renders overlay graphics on the media content. The client device activates at least one of input devices paired with the client device and the rendered overlay graphics. The client device further receives trigger responses over activated overlay graphics and displays an interactive view to enable delivery of service(s) in response to the trigger responses.

A computer system or computer-implemented process monitors a page rendering, including supplemental content rendered in one or more placement regions, for one or more viewability parameters. In response to a page event, the computer system or process selectively updates the one or more placement regions on the rendered page, based on a determination of whether the supplemental content of each placement region satisfied the one or more viewability criteria.