An online advertising system receives an advertisement from an advertiser. The system analyzes the advertisement, extracts its features and provides to the advertiser a quality rating for the advertisement which depends on a user engagement factor such as the predicted dwell time for the ad, given its features. The system further provides to the advertiser suggestions for improvements to the advertisement, such as a list of actionable guidelines that can improve the expected dwell time of the ad, and likely its conversion rate.

Techniques to measure consumption of content pages comprising a plurality of distinct content assets are disclosed. In various embodiments, content consumption signal data gathered by a plurality of clients, the content consumption signal data reflecting for at least a subset of content pages user engagement by content asset comprising the content page, is received. The received content consumption signal data and content attribute data associated with each respective content page are used to compute for each content page a content consumption metric reflecting an amount of content determined to have been consumed.

A computer program product enables an advertisement audience dynamical detection circuit to conduct an advertisement audience quantity detecting operation. The advertisement audience quantity detecting operation includes: receiving a probe request frame transmitted from other wireless communication device; recording the arrival time of the probe request frame; inspecting the frame field configuration of the probe request frame; allocating the probe request to a corresponding data group according to the arrival time and frame field configuration of the probe request frame and a sequence control value in the header of the probe request frame while ensuring all probe request frames in the same data group have same frame field configuration; and calculating an estimated quantity of advertisement audiences passing through a specific location in a specific time period based on a total quantity of resulting data groups.

Sample size determination techniques in sequential hypothesis testing in a digital medium environment are described. The sample size may be determined before a test to define a number of samples (e.g., user interactions with digital marketing content) that are likely to be tested as part of the sequential hypothesis testing in order to achieve a result. The sample size may also be determined in real time to define a number of samples that likely remain for testing in order to achieve a result. The sample size may be determined in a variety of ways, such as through simulation, based on a gap between conversion rates for different options being tested, and so on.

A method and system receive consumer media consumption data and dynamically prioritize the allocation of marketing resources amongst a variety of media intellectual property (IP) assets and for a variety of media IP asset managers and owners to run automated targeted marketing campaigns. The system identifies patterns in consumer media consumption using a statistical model which detects media IP assets demonstrating a high likelihood of realizing an efficient marketing opportunity. The efficiency of a marketing opportunity is evaluated using a statistical model based on the identification of customers who are most likely to increase the frequency with which they stream the assets after being exposed to them via a marketing action in addition to the projected costs of reaching this audience. The system automatically constructs a marketing campaign. The campaign is presented to the asset manager/owner in a graphical user interface (GUI) which enables the option to purchase and execute the marketing actions. Conditional on the execution of the marketing actions, the system performs an analysis on the efficacy of the marketing actions.

Methods, systems and apparatus for identifying illegitimate selections of content items. In some implementations, one or more servers can receive display data specifying a display state of a web page in a viewport. The web page includes a content item. Display instances are identified. A display instance is a display of at least a portion of the content item in the viewport. Selection instances of the content item are identified. A selection instance is a selection of the content item. The server(s) determines whether a selection of the content item occurred during a display of at least a portion of the content item in the viewport based on the display instances and the selection instances. A selection of the content is defined as an illegitimate selection if the selection did not occur during a display of at least a portion of the content item in the viewport.

Techniques and systems are described for analyzing components of digital content. A computing device of an analytics system receives user interaction data that describes an effect of user interaction with a plurality of items of digital content on achieving an action. The analytics system identifies which of a plurality of components are included in respective items of digital content. The analytics system then generates outcome data describing a likely effect of the plurality of components on achieving the action based on association with respective items of digital content. Additionally, the analytics system generates a recommendation to configure a subsequent item of digital content based on the outcome data. The recommendation is based on the likely effect of the different ones of the plurality of components, to generate more effective digital content.

Systems and methods for dynamically tracking delivery and performance of digital advertising placed on non-personal devices in physical locations and integrating, displaying, and reporting impressions and events in digital advertising systems.

A system is provided for interpretable viewing interest. A transformer with multi-head self-attention derives different hierarchical orders of input features. Hierarchical attention layers (i) aggregate the different hierarchical orders to obtain aggregated single-order feature representations and (iii) derive aggregation attention weights for the different hierarchical orders based on an applied order of the hierarchical attention layers. An attentional scoring layer evaluates the aggregated representations to output a significance of each order with respect to various CTR predictions. A hierarchical interpretation layer determines a respective importance of each input feature in various combinations from which the various CTR predictions are derived based on the aggregation attention weights and the significance of each order. A display device displays each of the various combinations for the various CTR predictions along with the respective importance of each of the constituent one of the input features in the various input feature combinations.

A method and apparatus for providing Web advertisements to online users is disclosed. A balanced set of negative data points and positive data points is derived from a log of Ad impressions and used to train a classifier. In response to an Ad request signal, a plurality of Ads is retrieved from a database. The Ad request signal indicates a request to provide an Ad for a slot available on a Web page associated with a website. The signal is provided in relation to an access of the Web page by an online user and includes information related to the online user. A choice of an Ad is predicted based on the information related to the online user and the plurality of Ads. The Ad is provided to a Web server to cause display of the Ad on the slot when the Web page is displayed to the online user.