A system and method for cross platform product listing curation with social network integration is disclosed. A particular embodiment includes: gathering seller information including identifiers of sellers of products listed on at least one peer-to-peer seller platform; obtaining product information corresponding to products listed by the sellers, the product information including product characteristics corresponding to the products listed by the sellers; retrieving potential product buyer information, the potential product buyer information including information indicative of buyer characteristics and buyer contact information of at least one potential buyer; matching the at least one potential buyer with a specific product listed by a specific seller using the product information and the potential product buyer information, the matching including correlating the product characteristics with the buyer characteristics of the matched potential buyer; and initiating contact between the matched potential buyer and the specific seller using the seller information and the buyer contact information.

Embodiments described herein provide approaches for detecting anomalies in electronic communications. Specifically, a set of response metrics is obtained from each of a plurality of communications. Each of the plurality of communications is part of a communications batch. Based on an aggregation of the response metric over the plurality of communications, a response metric value for one or more of the set of response metrics is computed. This response metric value is compared to a predicted metric value corresponding to the response metric. Based on this comparison, it is determined whether the response metric value is anomalous. If the response metric value is anomalous, a remediation activity is performed.

Systems and methods are described for a more accurate system for targeting specific users for advertising. An advertisement-suitability score associated with each of a plurality of users may be determined and users may be split into subsets. Those users whose advertisement-suitability score is within a threshold of a target may be identified and selected to receive an advertisement. From the rest of the users, those who have already seen an advertisement for the target-product may be identified, and a determination may be made of how many times a user is exposed to an advertisement before the user buys a product. Those users whose advertisement exposure is within a certain threshold of the number of times a user is exposed to an advertisement before the user buys a product may be identified and an updated advertisement-suitability may be calculated so that more users can be targeted to receive an advertisement.

A method for real-time measurement of campaign effectiveness includes: storing device profiles, each including a hashed device identifier, geographic location, and transaction entries including a transaction date and transaction data; receiving a data request including a start date, end date, merchant identifier, a plurality of device identifiers, and, for each device identifier, a category identifier of a set of category identifiers; generating a hashed identifier for each of the device identifiers; identifying, a device profile for each hashed device identifier; calculating purchase behaviors for each category based on transaction data in transaction data entries that include a transaction date between the start date and end date that are included in each identified device profile that is associated with the respective category and includes a geographic location corresponding to the merchant identifier; and transmitting at least one of: the calculated purchase behaviors and one or more metrics based thereon.

Example methods and apparatus to de-duplicate impression information are disclosed. An example method includes extracting, by executing a first instruction with a processor, characters from first cookies stored in a first memory space, the first cookies collected from client devices via network communications, and in response to the processor determining that at least two of the first cookies (1) include a same pattern of characters, and (2) correspond to a same first demographic, executing a second instruction with the processor to store, in a second memory space, the pattern of characters in association with the first demographic to indicate that the pattern of characters and the first demographic are both representative of a same first unique audience member.

The disclosure includes a system and method for stitching image frames. The system includes a processor and a memory storing instructions that, when executed, cause the system to: receive image frames that are captured by two or more camera modules at a particular time; interpolate a virtual camera between a first set of camera modules from the two or more camera modules; determine a set of disparity maps between the first set of camera modules; generate, based on the set of disparity maps, a virtual camera image associated with the particular time for the virtual camera from a set of image frames captured by the first set of camera modules at the particular time; and construct a left panoramic image and a right panoramic image associated with the particular time from the image frames captured by the two or more camera modules and the virtual camera image.

An embodiment may involve receiving, from one or more online advertising service devices at which one or more online advertising campaigns are operated, updates to information related to online advertisement placement and online advertisement performance associated with the one or more online advertising campaigns. The information may include a plurality of metrics. The embodiment may also involve receiving, via selectable graph menu options on a graphical user interface of a client device, a selection of two of the plurality of metrics. The embodiment may further involve transmitting, for display on the graphical user interface, data representing values of the selected two metrics over a pre-defined period of time. Reception of the data may cause the client device to plot a graph indicating the values of the selected two metrics over the pre-defined period of time.

A social networking system dynamically adjusts a number of advertisements presented to a user along with organic content items by modifying a ranking including organic content items and advertisements. Partial engagement scores are generated for organic content items based on an expected amount of user interaction with each organic content item, and scores are generated for advertisements based on expected user interaction and bid amounts associated with each organic content item. An engagement score measuring the user's estimated interaction with a content feed including organic content items without advertisements and an additional engagement score measuring the user's estimated interaction with a content feed including organic content items and advertisements are determined from the partial engagement scores and the scores. A difference between the additional engagement score and the engagement score modifies a conversion factor used to combine expected user interaction and bid amounts to generate advertisement scores.

An online system presenting advertisement content determines a bid amount for an advertisement for each new impression opportunity based on a budget for an advertising campaign provided by the advertiser, pacing bid amounts to spend the budget over the course of the advertising campaign. The online system applies an additional constraint that limits a cost metric for the advertising campaign such as an observed CPM (cost per thousand impressions) to a multiple of an average CPM for a target audience for presentation of advertisements of the advertising campaign. To compute the average CPM for the target audience, the online system samples users in the target audience and retrieves an average CPM for each online system user, and averages the retrieved per-user average CPMs.

Television is the largest advertising category in the United States with over 65 billion spent by advertisers per year. A variety of different targeting algorithms are compared, ranging from the traditional age-gender targeting methods employed based on Nielsen ratings, to new approaches that attempt to target high probability buyers using Set Top Box data. The performance of these different algorithms on a real television campaign is shown, and the advantages and limitations of each method are discussed. In contrast to other theoretical work, all methods presented herein are compatible with targeting the existing 115 million Television households in the United States and are implementable on current television delivery systems.