Protected audience selection system. Media consumption histories of browsers which have converted are received at a modeling system where targeting of browsers is prohibited. A model is built by determining a frequency of each respective media consumption event among the histories and comparing each determined frequency of a respective media consumption event to a frequency of the respective media consumption event among a population of browsers without the conversion event. The model is sent to a targeting system which excludes conversion events. A description of the conversion event is received at the targeting system. A history of a targetable browser is received at the targeting system. The model is applied to the history of the targetable browser at the targeting system, where conversion events have been excluded from the history. Advertising content is sent to the targetable browser according to a result of applying the model.

A system and method for providing and synthesizing data for publishers operating in the connected television ecosystem. Data from third party reporting platforms may be combined to present a unified view. Audience engagement may be measured, observed, and combined in a novel manner, providing unique insights to users.

Disclosed herein are a method and system that utilize a programmed content predictor to dynamically select electronic publishing content. In particular, the content predictor applies a selection model to select content for one or more selected webpages presented during an electronic transaction. The selection model utilizes a set of one or more machine learning models to select content based on calculated quality scores. The nature of the quality scores determined by the quality score model depend on the particular application. The predictor generates and populates a permutation quality table based on a set of selected content items and page variant, wherein the page variant defines locations of content positions within a webpage. The predictor then consumes the selection model to select a best permutation of content item-content position combinations to be returned for display on a webpage.

The disclosed subject matter relates to a system and method for selecting/recommending ads based on a contextual bandit approach. The disclosed approach leverages various embedding vectors of item, search, page taxonomy trained based on traffic data via advanced deep learning models, and uses model signals (e.g. historical CTR, item price, rating, quality) from other ad placements. The learning mechanism on top of the current methodology to automatic chooses the best feature sets and adjust model performance over time. The contextual bandit model performs better with respect to CTR than the Thompson Sampling model, and achieves lower regret and faster convergence over time.

The systems and methods described herein may be used to recommend an item to a consumer. The methods may comprise determining, based on a collaborative filtering algorithm, a consumer relevance value associated with an item, and transmitting, based on the consumer relevance value, information associated with the item to a consumer. A collaborative filtering algorithm may receive as an input at least one of: a transaction history associated with the consumer, a demographic of the consumer, a consumer profile, a type of transaction account, a transaction account associated with the consumer, a period of time that the consumer has held a transaction account, a size of wallet, a share of wallet, and/or the like.

An audience measurement computing system for monitoring a media presentation device in a monitored environment is described and includes a network interface, at least one processor, and a non-transitory computer-readable medium comprising instructions executable by the processor(s). The computing system is configured to obtain, via a cable connected to an input port of the media presentation device, a voltage signal generated by the media presentation device based on an operational state of the media presentation device; compare voltage indicated by the voltage signal to a threshold; based on the comparing, generate timestamped operational state data comprising a record indicative of when the media presentation device is in an on-state; obtain audience measurement data representing one or more media signals communicated to the media presentation device; and transmit, via the network interface over a network and to a central facility, the timestamped operational state data and the audience measurement data.

In general, embodiments of the present invention provide systems, methods and computer readable media for ranking promotions selected for recommendation to consumers based on predictions of promotion performance and consumer behavior. In embodiments, a set of promotions to be recommended to a consumer can be sorted and/or ranked according to respective relevance scores representing a probability that the consumer's behavior in response to the promotion will match a ranking target. In embodiments, calculating scores is based on a relevance model (a predictive function) derived from one or more contextual data sources representing attributes of promotions and consumer behavior. In embodiments, an absolute relevance score represents an absolute prediction of a ranking target variable. In embodiments, absolute relevance may be used to determine personalized local merchant discovery frontiers; featured result set thresholding for impressions; and/or promotion notification triggers. In embodiments, predictive models based on gross revenue may be optimized using promotion category-dependent price boosting.

The present disclosure provides for management of impressions in advertisement campaigns. Impressions may be moved between different impression media based on performance metrics and historical data. Impression budgets may be modified in an active campaign based on forecasts determined using current performance data. Impression budgets may be reallocated between simultaneously active advertisement campaigns.

Systems and methods are provided for determining a quantity of network location visitors that are likely generated or encouraged by specific offline events. A corresponding number of leads may then be attributed to and associated with those specific events. Ongoing conversion activity of those visitors may be tracked and associated with the offline events. Conversions of those visitors may be attributed entirely or partially to one or more specific offline events. The effectiveness of each offline may then be evaluated based on aggregate lead and conversion information.

A method for providing survey consumer data to a centralized server via a consumer panel application is provided. The method includes receiving in a server, from an application installed in a mobile device of a consumer, a transaction data linking a consumer identification with a selected retailer and associating a consumer segment with the transaction data based on a demographic attribute shared between a server account for the consumer and the consumer segment. The method also includes determining a sales lift factor for the consumer segment based on an adjustment factor and the transaction data, and updating a scalable measurement protocol in the application installed in the mobile device of the consumer based on the sales lift factor. A system and a non-transitory, computer-readable medium storing instructions to perform the above method are also provided.