Abstract: Based on prior interactions associated with a user, an online system predicts an amount of interaction by the user with an object associated with an advertisement. Using the predicted amount of user interaction, the online system determines an expected value of presenting the advertisement to the user. The advertisement is ranked among other advertisements based on the expected values associated with the advertisements, and one or more advertisements are selected for presentation to the user based on the ranking. An advertisement may also specify a threshold amount of interaction with an associated object as targeting criteria, so the predicted amount of interaction with the object associated with the advertisement may determine if a user is eligible to be presented with the advertisement.

Abstract: A method delivers information to satisfy current needs of a driver of a vehicle, by first acquiring data related to a current state of the vehicle. The current state and a predictive model are passed to a predictive procedure to determine choice probabilities for nodes in a choice tree (CT). Based on the choice probabilities, information related to the current needs to the driver are selected from a database storing commercial and non-commercial information. Then, the information is delivered to the driver, wherein the delivering is autonomous of the driver.

Abstract: Based on prior interactions associated with a user, an online system predicts an amount of interaction by the user with an object associated with an advertisement. Using the predicted amount of user interaction, the online system determines an expected value of presenting the advertisement to the user. The advertisement is ranked among other advertisements based on the expected values associated with the advertisements, and one or more advertisements are selected for presentation to the user based on the ranking. An advertisement may also specify a threshold amount of interaction with an associated object as targeting criteria, so the predicted amount of interaction with the object associated with the advertisement may determine if a user is eligible to be presented with the advertisement.

Abstract: A posterior probability calculating apparatus that calculates the posterior probability in a short time includes a user information storage unit, a prior probability calculating unit, a likelihood calculating unit, an accepting unit, a posterior probability calculating unit, and an output unit. The user information storage unit stores user information that associates a user attribute and log information. The prior probability calculating unit calculates the prior probability that a user has a certain user attribute. The likelihood calculating unit calculates the likelihood that a user with a certain user attribute has performed a certain event. The accepting unit accepts calculation target information. The posterior probability calculating unit calculates the posterior probability that a user who has performed an event included in log information included in the accepted calculation target information has a user attribute included in the calculation target information.

Abstract: Embodiments of the disclosed invention include a system and a method for providing location-based services to consumers of a shopping facility. In one embodiment, a consumer creates a user account, user profile, and registers one or mobile devices. The system monitors for the presence of the registered mobile devices within one or more shopping facilities. The system transmits advertising material corresponding to the user created profile to a detected registered mobile device in response to the registered mobile device being within a specified range of a store associated with the user created profile.

Abstract: A computer-implemented system and method for establishing media data exposure, where a media device, such as a computer, radio, television and the like, receive media data and produces research data from it. The research data may be based on computer-based or computer network-based characteristics, ancillary codes or audio signatures. As the research data is being produced, an inductive coupling is sought for nearby portable computer devices. Once a portable computing device inductively couples to the media device, information is transferred, allowing a system to determine and/or verify that specific users were exposed to particular media data.

Abstract: A method, apparatus, system, and computer program product provide the ability to bid for an advertising impression. Within an advertising exchange, an advertising bidding impression campaign to bid for the advertising impression is initialized. A desired impression quality rank is selected and a bid against the desired rank is accepted. An actual impression quality rank for an actual advertising impression in an advertising impression inventory is determined. Based on the bid and the actual impression quality rank, the actual advertising impression is awarded to the bidder.

Abstract: In one embodiment, a method determines advertisement (ad) impressions previously determined for a site and respective predicted probabilities determined for the ad impressions. A mapping table is generated mapping predicted probabilities to respective precisions using seed data associated with the ad impressions. The method generates optimal options for using the first level and the second level for the segment using the mapping table. The optimal options include a first precision for the first level, a second precision for the second level, and a ratio of ad inventories allocated to the first level and the second level. Then the method selects one of the optimal options. The selected one of the optimal options includes parameters including a first threshold for the first level, a second threshold for the second level, and the ratio that are used to test whether a predicted probability for an ad impression is targeted to the first level or the second level.

Abstract: The present invention relates to the measurement of human activities through video, particularly in retail environments. A method for measuring retail display effectiveness in accordance with an embodiment of the present invention includes: detecting a moving object in a field of view of an imaging device, the imaging device obtaining image data of a product display; tracking the object in the field of view of the imaging device to obtain a track; and obtaining statistics for the track with regard to the product display.

Abstract: An application framework for mobile devices may provide a variety of application modules directed towards enterprise brand extension. The application modules are organized into five main categories: (1) featured, (2) community, (3) play/engage, (4) media, and (5) shop. The “featured” category may allow enterprises to push specific content onto its consumers. The “community” category may allow enterprises to leverage social networks and consumer communities that build and expand around their brands. The “play/engage” category may allow enterprises to offer compelling value and engaging utility to its customers. The “media” category may allow enterprises to entertain, inform, and educate consumers about brands through media content. The “shop” category may allow enterprises to facilitate electronic commerce with its customers. Further application analytics may be utilized by aggregating affiliate, sales, or usage data, etc.

Abstract: Profiling based advertising and commerce systems are provided herein. The system statistically analyzes user activity data of social network users and normalizes the statistical data with respect to specified user populations. Then the system profiles each user with respect to user archetypes using empirical study data that correlates the user archetypes with respective normalized statistical activity data relating to the user. The correspondence analysis is carried out by applying a heuristic genetic algorithm on an artificial neural network that represents the relation between the normalized user study data and the user archetypes. Profiles and segmentations produced are used for designing advertising campaigns and electronic commerce.

Abstract: Various of the disclosed embodiments contemplate television viewing behavior data collected from a plurality of television set top boxes by using aggregation to detect an excess or a deficit in viewership for a group of television set top boxes. In some embodiments, a group of set top boxes can be associated with a particular television service provider, cable television head-end, or data warehouse. Additionally, some embodiments can clean television viewing behavior data by detecting and correcting aberrant viewership in a time series, e.g. based on a weekly or an approximately monthly frequency. In some embodiments, the aberrant viewership can be detected by calculating a minimum expected number of viewers for a day and comparing it to the actual number of households that reported viewers for that day.

Abstract: A system and process for improving product recommendations for a first user includes receiving a request for one or more product recommendations for a first user, each product recommendation being associated with any one of a plurality of retailers, receiving a plurality of recommendation sets from one or more automated product recommendation systems, wherein the plurality of recommendation sets are generated using different selection models and using ensemble learning to select one or more most relevant product recommendation sets from the plurality of product recommendation sets.

Abstract: 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.

Abstract: A system and method for management of advertisements is described. Advertised results may be provided based on a ranking and a matching of an advertisement with a sponsored answer and/or an organic result to a query. An advertisement may be provided using a human assistant.

Abstract: A content-targeting ad system is provided with a user behavior (e.g., selection (e.g., click), conversion, etc.) feedback mechanism. The performance of individual ads, or groups of ads, may be tracked on a per document (e.g. per URL) and/or on a per host (e.g. per Website) basis. The performance of ad targeting functions may also be tracked on a per document, and/or per host basis. Such user behavior feedback data may be processed (e.g., aggregated) into useful data structures. Such user behavior feedback data (raw or processed) may then be used in a content-targeting ad system to improve ad quality, improve user experience, and/or maximize revenue.

Abstract: One embodiment of the present invention sets forth a technique for recommending digital content to a user of a digital content application based on continually learned patterns of behavior. Based on metrics collected from a current session of the digital content application, properties associated with one or more users interacting with the application are inferred. The inferred properties are matched against previously defined patterns of behavior to identify digital content that could be presented to the one or more users for optional selection.

Abstract: Relationships between a plurality of mobile devices are automatically determined. For each mobile device in the plurality of mobile devices, characteristics of a user of the mobile device are determined. Based on the characteristics of the users of the mobile devices, a first role of a first user of a first mobile device is determined. Based on the characteristics of the users of the mobile devices, a second role of a second user of a second mobile device is determined. Based on the first role and the second role, a relationship between the first user and the second user is determined. A determination is made that a relationship between the first mobile device and the second mobile device is equal to the relationship between the first user and the second user.

Abstract: Techniques for estimating advertisement inventory for search retargeting segments are provided. A total inventory for each cluster of a plurality of clusters is estimated based on a history of previously viewed pages and previously used search keywords that were submitted by users is searches performed prior to accessing the previously viewed pages. A search retargeting (SRT) segment is received that includes a set of search keywords. The SRT segment is received in a request for deliverable advertisement inventory for advertisements associated with the SRT segment. A deliverable inventory for the received SRT segment is estimated based on the estimated total inventories for the clusters.

Abstract: An advertising statistics collection system employs multiple peers, a signing server and a collection server to ensure peer privacy when the statistics are gathered. A peer relay system aids in providing anonymity for a given peer in a peer-to-peer network environment with little or no trust between communicating parties. Peers are additionally protected by a randomly generated identifier that can be used to globally gather statistics on the peer without revealing the peer's identity.

Abstract: A computer-implemented method is described for determining a response attribution value that represents a credit assignment to a communication, for an associated response received from a recipient during a marketing campaign.

Abstract: A system 10 which receives content and which displays and communicates the content to an individual 100 according to certain rules.

Abstract: A system for obtaining metrics for online advertising uses multiple sources of user data, including panel data, social networking system data, and user data from other online service providers. To avoid data leakage that could occur if the different providers were to share their user data, an advertising server accesses user data from the various sources and applies rules for obtaining the advertising metrics from the various user data sources. The rules may determine what data to use when there are conflicts between the different sources. Derived data may also be used to provide an indication of underlying demographics data without revealing personal information from the data source.

Abstract: An online ad provisioning system couples persuasive media items (ads) with an established viewership/recipient set by first identifying a popularity, or number of recipients of a requested media item, and subsequently associating the media item with an advertisement (banner, window, video segment) expecting the established viewership. While conventional advertising seeks to divert the readers attention before their eyes are on the page, the system identifies and targets recipients after their eyes are on the page (or screen, window, etc.). Such an association allows an advertiser to specify, for example, to associate an ad (persuasive media item) with the most popular web page, or to run a commercial in a video stream only if at least a predetermined number of viewers are receiving the stream.

Abstract: A method of determining which customers to target during marketing is disclosed. Parameters are estimated from inputs of sample customers from statistical procedures, and an approximation model is created for each of the estimated parameters. The approximation models are applied to transaction data collect for customers on a customer list. For each customer, the transaction data is applied to the approximation models to determine a dropout probability and a transaction rate. A likelihood of repeat purchase is determined for each customer based on the dropout probability and the transaction rate.

Abstract: In one implementation, a computer-implemented method includes receiving, at a computer system, a request to solicit one or more users to generate media content for a campaign; identifying, by the computer system, a plurality of content creating users; obtaining demographic data for a plurality of content consuming users who have accessed the media content that was generated by the plurality of content creating users; determining distributions of the plurality of content consuming users across a plurality of demographic categories; selecting, by the computer system, a portion of the plurality of content creating users based on a comparison of i) the one or more parameters for the campaign and ii) the distributions of the plurality of content consuming users across the plurality of demographic categories; and providing information that identifies an opportunity to generate media content for the campaign.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for estimating demographic compositions of television audiences from audience similarities. In an aspect, pairwise cosine similarities of segment of viewers of rated and unrated television programs are determined, demographic information of rated programs is attributed to the unrated programs from the cosine similarity measures and demographic information for the rated programs.

Abstract: A method, apparatus and computer program product for performing targeted advertising in documents is presented. A document is identified as having advertisements associated therewith. A statistical ranking of terms derived from said document is received and at least one term is selected from the results to use as a keyword for associating at least one advertisement with the document. The at least one term is stored with the document. When the document is viewed, the document is identified as being enabled to have advertisements associated therewith. The at least one stored term is retrieved from the document and is submitted to an advertisement aggregator. At least one advertisement is received from the advertisement aggregator and is rendered with the document.

Abstract: The disclosure is related to an advertisement service using mobile vehicles. Particularly, the disclosure relates to providing advertisement content selected based on statistical information on an advertisement target at an advertisement display location. Furthermore, the selected advertisement content may be provided to a corresponding mobile vehicle before the corresponding mobile vehicle arrives at the advertisement display location.

Abstract: Machines, systems and methods for managing reach of an advertisement campaign, the method comprising selecting an initial seed of one or more keywords, such that the initial seed is pertinent to a target audience with known interests and demographics; receiving at least one candidate keyword to be added to the initial seed; determining effectiveness of the candidate keyword based on relevancy, expansion and redundancy parameters associated with the candidate keyword; and expanding the initial seed by adding the candidate keyword, in response to determining that the candidate keyword meets a threshold measure for effectiveness.

Abstract: Embodiments of a mobile device and server system are described. The mobile devices communicate with the server system and present targeted content, such as advertisements to the mobile device users. The content is targeted based on usage statistics stored on the server system which were previously collected from the mobile device. The server receives the usage statistics collected from the mobile device, makes inferences about preferences of users by tracking application and/or content usage behaviors of the users, generates recommendations for advertisements targeted toward the users of the mobile devices based on usage statistics; and transmits the recommendations to one or more of the mobile devices for presentation to the user(s).

Abstract: In one aspect, a computing apparatus is configured to profile the spending distribution of users who have made purchases from a merchant and who have paid for the purchases via a transaction handler (e.g., using credit cards, debit cards, prepaid cards). The spending distribution is determined based on transaction data of the users, where the transaction data records the transactions of the users for purchases from various merchants. The spending distribution is profiled to indicate the preference of the customers of the merchant as a whole and thus can be used to customize the ratio of media content provided to the customers of the merchant, such as the presentation ratio of advertisements from different merchants, or from merchants of different categories.

Abstract: A system and method for effectively supporting software distribution in an electronic network includes a software server and a network of client devices. The software server stores software items received from a software provider. The software items include various types of trial software that is provided to device users for temporary evaluation and potential purchase. A recommendation engine of the software server creates recommendation lists to identify optimal candidates from among the stored software items for performing an automatic and transparent software download procedures. The recommendation engine creates the recommendation lists by analyzing selectable software-ranking criteria related to device users of the client devices. The software server then downloads the optimal candidates from the stored software items to respective target devices during the software download procedures.

Abstract: In one aspect, a computing apparatus is configured to profile the spending distribution of users who have made purchases from a merchant and who have paid for the purchases via a transaction handler (e.g., using credit cards, debit cards, prepaid cards). The spending distribution is determined based on transaction data of the users, where the transaction data records the transactions of the users for purchases from various merchants. The spending distribution is profiled to indicate the preference of the customers of the merchant as a whole and thus can be used to customize the ratio of media content provided to the customers of the merchant, such as the presentation ratio of advertisements from different merchants, or from merchants of different categories.

Abstract: A media targeting system and method uses visual pattern recognition techniques in association with consumer transactions as the basis for building a targeting database, which is then later used for automated consumer identification and targeted advertising purposes. The invention solves the problem of generating a large scale, robust media targeting database without relying on active or passive participation by consumers. Also disclosed are other demographics estimation systems and methods which facilitate less expensive media targeting capabilities which can be used in conjunction with the more robust transaction associated method disclosed.

Abstract: Methods, systems, and apparatus, including computer program products, for ranking search results for queries. The method includes calculating a visual similarity score for one or more pairs of images in a plurality of images based on visual features of images in each of the one or more pairs; building a graph of images by linking each of one or more images in the plurality of images to one or more nearest neighbor images based on the visual similarity scores; associating a respective score with each of one or more images in the graph based on data indicative of user behavior relative to the image as a search result for a query; and determining a new score for each of one or more images in the graph based on the respective score of the image, and the respective scores of one or more nearest neighbors to the image.

Abstract: Events generated by customer interaction during an internet-based session are made available for use by a system for tracking the effectiveness of web advertising campaigns. Event occurrences are collected for evaluation to determine whether campaign goals are being met. Campaigns are defined by rules indicating which ad content is to be displayed to which customers. Event types to be reported are selected depending on the needs of the particular campaign.

Abstract: The disclosure includes a system and method for performing actions using visual search. The system includes a controller, an image recognition module and a polling engine. The controller receives data describing an image that is associated with a poll from a first user. The image recognition module identifies the image as being an option that is selected by the first user for the poll. The polling engine associates the option selected by the first user and a first set of demographic information describing the first user with the poll. The polling engine provides the first user with polling data that describes one or more voting results for the poll. The polling data includes a second set of demographic information associated with one or more second users that provided an answer to the poll.

Abstract: Methods, systems and computer program products for inferring a value of a visitor property for a visitor to a web destination are described. A set of traversals indicating visits to web destinations are received, including scored and unscored traversals. Initial destination scores for the web destinations visited by the scored traversals are inferred based on the known scores of the scored traversals. Initial scores for the unscored traversals are estimated based on the initial destinations scores. Revised destination scores for the web destinations visited by the scored traversals and initial destination scores for the web destinations only visited by the unscored traversals are inferred. Revised scores for the unscored traversals are estimated based on the revised destination scores and initial destination scores. Revised destination scores for all of the web destinations are inferred based on the scores of the scored traversals and the revised scores of the unscored traversals.

Abstract: This paper presents a practical method for measuring the impact of multiple marketing events on sales, including marketing events that are not traditionally trackable. The technique infers which of several competing media events are likely to have caused a given conversion. The method is tested using hold-out sets, and also a live media experiment for determining whether the method can accurately predict television-generated web conversions.

Abstract: Tools and techniques for determining click values are described herein. A method for determining click values may include processing transaction history records. These records may be related to transactions that are conducted between visitors and a website. The method may also include computing respective click values associated with different visitors, based on the transaction history records involving those visitors. These click values indicate a likelihood that the visitors may transact for particular goods or services offered through the website.

Abstract: Tunable algorithmic segment techniques are described. In one or more implementations, a target audience definition is obtained that is input to initiate creation of a look-alike model. The target audience definition indicates traits associated with a baseline group of consumers who have interacted with online resources in a designated manner, such as by buying a product, visiting a website, using a service, and so forth. Tuning parameters designated for the look-alike model are ascertained and the look-alike model is built based on the target audience definition and the tuning parameters. The tuning parameters may include at least a setting selectable to control reach versus accuracy for the look-alike model. Segment data indicative of market segments generated according to the look-alike model may then be exposed for manipulation by a client. The manipulation may include selectable control over the tuning parameters to generate different look-alike groups from the segment data.

Abstract: A system uses neuro-response information to evaluate content within a cluster, such as commercials in a pod, advertisements in a frame, or products on a shelf, to determine priming characteristics associated with each pieces of content within the cluster. The priming characteristics and other data are combined to obtain blended attributes. The blended attributes are correlated with each piece of intracluster content to allow intelligent management including selection, arrangement, ordering, presentation, and/or scheduling of intracluster content. Intracluster content may also use priming characteristics associated with extracluster content to further improve management.

Abstract: An advertisement delivery management apparatus according to an embodiment includes an acquisition unit, a determination unit, and an accepting unit. The acquisition unit acquires information on two or more types of delivery target user groups, each including a plurality of delivery target users predicted as future advertisement delivery destinations. The determination unit determines whether each of the delivery target user groups satisfies delivery conditions designated by an advertisement delivery order request. The accepting unit accepts the advertisement delivery order request based on the determination result of the determination unit.

Abstract: A system and method for implementing electronic advertising which provides content to users based on observing behavior of certain trendsetters within a member population. The trendsetters are determined by studying historical adoption behavior of individuals within the member population, or by reference to known indicia.

Abstract: A computer-implemented method for displaying advertisements to members of a network comprises identifying one or more communities of members, identifying one or more influencers in the one or more communities, and placing one or more advertisements at the profiles of one or more members in the identified one or more communities.

Abstract: An advertisement delivery management apparatus according to the present disclosure includes a score determining unit and an allocating unit. The score determining unit determines an allocation score representing a adequacy degree of allocation of a delivery target user on an advertisement delivery order request based on the number or the proportion of non-allocated users which are delivery target users which are not allocated on the advertisement delivery order request among a plurality of delivery target users for each user attribute. The allocating unit allocates the delivery target user on the advertisement delivery order request so that a decrease in the allocation score is minimized before and after the delivery target user is allocated on the order request for the advertisement delivery order request.

Abstract: Requests for content are received, for example, an HTTP request for a web page is received. Each request has a landing context, which may include information about the user sending the request, the request itself, the referrer, or another subject. This information can be found in the requests or external to the requests. The information of the landing context is compared to appropriate triggering criteria. For requests that satisfy the appropriate triggering criteria, a destination is provided based on one or more weighted treatments. The request is directed to the provided destination. The results of the requests are subsequently analyzed and used to adjust the treatments in an automated fashion.

Abstract: A computer-implemented method is described for determining a response attribution value that represents a credit assignment to a communication, for an associated response received from a recipient during a marketing campaign.

Abstract: A computer implemented method comprises analyzing a plurality of attributes of a sample of online documents using a boosted decision tree and generating a model from it. The model is used to predict a click through rate (CTR) of an additional online document based on the analyzing. The predicted CTR is output to a display device, storage medium or network.