Disclosed is a method that includes: profiling a set of mobile applications according to revenue-related parameters; tracking a user's interaction with a mobile application; scoring the user's interaction levels, and based on the score, grouping users into mobile analytics groups associated with the targeting profiles; facilitating the transmission of user information, user interaction data, and specific mobile analytics groups to advertising campaigns. The method may be executed on a digital device. A related system is disclosed.

A method of estimating a click-through rate is provided. According to the method of estimating a click-through rate, a click label is set for an exposure log based on a click log, wherein the exposure log records information of a page element presented to a user; an exposure weight corresponding to the exposure log is set based on the click label of the exposure log and a context similarity of the page element; click-through rate estimation is performed based on the exposure log set with the exposure weight.

A process is described for assessing the suitability of particular keyword phrases for use in serving contextually relevant content for display on pages of network-accessible sites. In one embodiment, the process involves scoring the key phrases based in part on collected user behavioral data, such as view counts of associated social media content items. A process is also disclosed in which selected keyword phrases on a page are transformed into links that can be selected by a user to view bundled content that is related to such keyword phrases.

A method of coupon distribution is used in connection with a demand response (DR) event. The method includes clustering DR customers into customer clusters based on energy use behaviors of the DR customers. Suggested coupons are received from merchants, each coupon including load serving entity (LSE) and merchant contributions. Based on energy price forecast, the suggested coupons, and customer information, a coupon distribution is found to maximizes a financial benefit to the LSE and includes an optimal number of the suggested coupons to be distributed to the customer clusters. The suggested coupons are distributed to the customer clusters per the coupon distribution and collecting responses to the suggested coupons indicating participation. Based on the customer responses, the method includes estimating energy curtailment contributions of the DR customers and an actual energy price for the DR event and communicating to an independent system operator an energy transaction bid based thereon.

Various technologies described herein pertain to prefetching content units. A prefetch request is transmitted to a server from a client device. The prefetch request includes data indicative of probabilities of slots for content units being available during an upcoming time period. The probabilities can be based on likely interaction with application(s) executed by the client device during the upcoming time period. Prefetched content units assigned to the client device for the upcoming time period can be received from the server responsive to the prefetch request. One or more of the prefetched content units can be served for display on a display screen of the client device during execution the application(s). Further, statuses of the prefetched content units can be monitored, and information that specifies a subset of the prefetched content units that are unlikely to be displayed on the display screen prior to corresponding deadlines for expiration can be transmitted.

Recommendation systems and techniques are described that use linear stochastic bandits and confidence interval generation to generate recommendations for digital content. These techniques overcome the limitations of conventional recommendations systems that are limited to a fixed parameter to estimate noise and thus do not fully exploit available data and are overly conservative, at a significant cost in operational performance of a computing device. To do so, a linear model, noise estimate, and confidence interval are refined by a recommendation system based on user interaction data that describes a result of user interaction with items of digital content. This is performed by comparing a result of the recommendation on user interaction with digital content with an estimate of a result of the recommendation.

A computer-implemented system and method for category-based contextual advertisement generation and management are disclosed. The system in an example embodiment includes an advertisement processor to allocate a first display region for displaying a combination of variable revenue ads and fixed price ads, the variable revenue ads and the fixed price ads being category-based, sort the variable revenue ads based in part on a user entered variable revenue value, and sort the fixed price ads based on a rotation.

Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium, for providing content. A method includes receiving a request for an advertisement to be displayed in a slot associated with a third-party content site; identifying a relevant advertisement to be provided in the slot; determining information to be included in an annotation associated with the advertisement, the annotation including customized information to be presented along with the advertisement; providing the advertisement responsive to the request including providing the annotation along with a control for re-publishing the advertisement along with the relevant advertisement; receiving user input selecting the control and designating the advertisement for re-publishing to a group, the group being designated by the user; and targeting additional content to the group based on the received user input.

The subject technology identifies obfuscated email events received from one or more internet service providers (ISPs). The data deobfuscation layer may identify email messages including obfuscated open events and locations by monitoring the open rates of email messages received by different operating systems, ISPs, and/or device types. The data deobfuscation layer may determine accurate campaign level metrics and/or user open probabilities for batches of email messages having obfuscated events. For example, one or more machine learning models may predict an email open rate for one or more email campaigns and identify the users having the highest probability of generating a true open event. The data deobfuscation layer may be used to improve the performance of email communication networks and/or increase engagement metrics for media campaigns.

Systems and methods are provided for optimizing displays in one or more user interfaces. An exemplary method may include retrieving web entries from a database and generating a plurality of candidates based on the retrieved web entries, where each web entry of the web entries is a clickable item that is displayed on the one or more user interfaces. Additionally, provide the plurality of candidates for display on the one or more user interfaces and determine click-through rates for each of the plurality of candidates. Thereafter, create a display pool of candidates to display from plurality of candidates based on the click-through rates and update the display pool of candidates responsive to retrieving additional web entries from the database.