A system for training a bidding model comprising: a plurality of tactics stored on at least one database; a plurality of hyperparameters; in response to an available inventory from a publisher relayed through a real time bid server, computing a bid on the available inventory; sending the bid to the real time bid server; receiving an auction result in response to the bid; calculating a plurality of rewards based on the auction result and the tactics; calculate a plurality of q values based on the rewards; calculate a plurality of losses; backpropogating the losses through the bidding model.

Disclosed examples determine a duplicated audience size representative of panelists exposed to television media and digital media; determine a panel duplication reach based on the duplicated audience size and a panelist population; determine a did-not-view reach based on a television audience size, a digital audience size, the duplicated audience size, and the panelist population; obtain an overlap multiplier as a ratio of (1) a product of the panel duplication reach and the did-not-view reach and (2) a product of a television panel reach and a digital panel reach; determine a duplication factor for a media item based on a television audience reach, a digital audience reach, and the overlap multiplier; and determine a total audience for the media item based on the television audience reach, the digital audience reach, and the duplication factor.

A method is disclosed for tracking advertisement effectiveness. First information associated with desired advertising information is broadcast from at least one of a plurality of fixed information nodes. A mobile unit receives the broadcast information and outputs the desired advertising information. An advertisement counter is started at the time of receipt of the broadcast information and presence information is broadcast from at least one of a plurality of fixed monitoring nodes over a restricted broadcast range, which at least one fixed monitoring node is disposed in a predetermined fixed physical proximity with a vendor location. The broadcast presence information is received at the mobile unit and a presence counter is started in response to receipt of the presence information. At the mobile unit loss of receipt of the broadcast presence information, the presence counter is stopped.

Classification of the user of an attention application is moved from the cloud, where the classification is performed by advertisers based on trackers that follow a user, to the attention application itself. A user of the attention application controls inputs to the classification model and can exclude sensitive privacy information from inclusion in the classification model. The classification model is applied locally at the attention application to a catalog of advertisements and without revealing to trackers and advertisers whether attention was paid to particular ads. An analytics provider may have increased access to attention applications and can form ad campaigns and provide performance data thereon to advertisers without infringing attention user privacy. The system directs value away from trackers and advertisers and to attention application users and publishers.

This disclosure provides methods and systems for collecting statistics about exposure data and a device. In one implementation, a mobile terminal collects real-time location information of the mobile terminal to determine a location and a movement direction of the mobile terminal, and may further obtain a first identifier and orientation and location information of an advertising device. The mobile terminal collects statistics about first exposure duration of the advertising device for the mobile terminal. The server may receive the exposure data from a plurality of mobile terminals, and collect statistics about exposure traffic and an audience of the advertising device based on the exposure data.

An advertisement evaluation device includes: a first acquisition unit configured to acquire a first time in a case where first face authentication has succeeded for a first captured image obtained by imaging a predetermined user when the user enters a predetermined store; a second acquisition unit configured to acquire a second time in a case where second face authentication has succeeded for a second captured image obtained by imaging the user when the payment is made in the store; a registration unit configured to register a payment history based on the payment in association with the user; a calculation unit configured to calculate a stay time of the user in the store; and an evaluation unit configured to evaluate an advertising effectiveness of advertisement information presented to the user based on the payment history and the stay time.

Methods and apparatus to generate audience metrics using third-party privacy-protected cloud environments. An example apparatus includes at least one memory, programmable circuitry, and instructions to cause the programmable circuitry to generate a first demographic correction model based on a first matrix, the first matrix including first data indicative of user accesses to media, the first matrix associated with a first demographic, generate a second demographic correction model based on a second matrix, the second matrix including second data indicative of user accesses to the media, the second matrix associated with a second demographic, and generate predicted demographics of a user associated with the user accesses based on the first demographic correction model and the second demographic correction model, the predicted demographics including the first demographic and the second demographic.

A software and/or hardware facility for scoring the quality of traffic to a site accessible via the Internet or other network. The facility may generate training set data and use the training set data to identify parameters indicative of fraudulent traffic to a site and reduce the effect of fraudulent traffic advertisers and publishers. The facility may score the quality of traffic and determine combinations of parameters that are indicative of the quality of traffic to the site. Traffic to the site may be scored based on the combination of parameters associated with the one or more sessions. Lower scores are indicative of traffic having little value to a publisher, advertiser, or third party; higher scores are indicative of traffic having greater value.

A method, product and system for automatic fraud engagement adjustment. The method comprises, based on monitoring of engagements and conversions, determining a segment-specific estimated quality score of a traffic segment; determining an observation-based pair-specific quality score for the traffic segment and for a specific campaign; and automatically performing mitigating fraudulent engagements in the traffic segment by reducing, in real-time, a reward for engagements in the traffic segment with respect to the specific campaign, whereby aggregative reward mitigates rewards for fraudulent engagements without specifically identifying which engagements are fraudulent.

The present disclosure proposes an advertisement bidding device capable of inducing advertisers to actively participate in bidding by determining a trustee group that guarantees an advertising effect among recipients receiving an advertisement and providing information related to the trustee group to the advertisers as bidding information.