A system and method is provided for determining when an electronic correspondence is reviewed by a consumer, and referencing this information when generating a subsequent electronic correspondence. The information may be used to determine when to send the subsequent electronic correspondence to the consumer. For example, the subsequent correspondence may be sent at the same time of day as when the consumer is determined to have previously reviewed an electronic correspondence. The information may also be used to determine what to include in the subsequent electronic correspondence. For example, time-sensitive promotions that are selected based on the information identifying the previous time at which the consumer reviewed a previous electronic correspondence, may be included in the subsequent electronic correspondence.

A clustering and recommendation machine determines that an item is included in a cluster of items. The machine accesses item data descriptive of the item. The machine accesses a vector that represents the cluster and calculates the likelihood that the item is included in the cluster, based on the item variable and the probability parameter. The machine determines that the item is included in the cluster, based on the likelihood. The machine also recommends an item to a potential buyer. The machine accesses behavior data that represents a first event type pertinent to a first cluster of items. The machine calculates a probability that a second event type pertaining to a second cluster of items will co-occur with the first event type. The machine identifies an item from the second cluster to be recommended and presents a recommendation of the item to the potential buyer.

In one embodiment, a computing system receives a number of location updates sent by one or more users. These location updates may have different geographic locations, but refer to the same place or point of interest. Each location update corresponds to a user visit to the place or point of interest, and each location update is determined by a mobile client device of the corresponding user. The mobile client device may determine a location update by any one or more of a number of location methods available to the mobile client device. The computing system determines a ping compensation factor to be associated with the place or point of interest. The ping compensation factor is based on a total number of visits to the particular place, versus the subset of visits to the particular place determined by a first location method from the number of location methods.

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 present invention is a system and method for improving the accuracy with which marketing efficacy can be measured and improved using human behavioral insights. The process aligns at least two different data sets and normalizes the information by removing statistical bias. In a particular implementation motor vehicle data is collected by census of hotelier transaction data. The transaction data is overlaid upon observed vehicle data which is captured by a triggering event. The system statistically analyses the data resulting from the combined data sets and provides a report with a recommendation to a human user.

The present disclosure provides a detailed description of techniques used in methods, systems, and computer program products for associating anonymous information to personally identifiable information without sharing any personally identifiable information. A method receives a specification record comprising one or more specified demographic attributes to be used in user record selection operations, the results of which operations include user records that comprise a user identifier and at least some non-personally-identifiable information. A candidate group is formed by applying a set of rules over the retrieved user records to reject-out one or more user records that comprise mutually-exclusive characteristics with respect to the other user records in the candidate group. An anonymity measure is calculated over the candidate group to satisfy a threshold of anonymity. If needed to satisfy the threshold of anonymity, additional user records are added to the group before any sharing operations. Anonymity of the users is preserved.

Digital image selection techniques are described that employ machine learning to select a digital image of an object from a plurality of digital images of the object. The plurality of digital images each capture the object for inclusion as part of generating digital content, e.g., a webpage, a thumbnail to represent a digital video, and so on. In one example, digital image selection techniques are described that employ machine learning to select a digital image of an object from a plurality of digital images of the object. As a result, the service provider system may select a digital image of an object from a plurality of digital images of the object that has an increased likelihood of achieving a desired outcome and may address the multitude of different ways in which an object may be presented to a user.

A method including receiving, at a first computing system from a second computing system, a first key and encrypted online interaction data, receiving, at the first computing system from a third computing system, a second key and encrypted offline action data encoding data indicating one or more offline actions, receiving, at the first computing system from the third computing system, executable code comprising a third key, and executing, by the first computing system, the executable code. The executable code causing the first computing system to decrypt the encrypted online interaction data and the encrypted offline action data using the first key, the second key, and the third key, correlate one or more of the offline actions in the offline action data to one or more online interactions in the online interaction data, and generate aggregate data indicating a number of offline actions correlated to the online interactions.

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform functions comprising: receiving one or more vectors representing one or more types of features for a pair of items; generating, using a similarity item model of a machine learning architecture, a prediction for a similar item, wherein the similarity item model combines a pair of separately trained machine learning models; combining a first output of the gradient boosted model and a second output of the neural network model to generate a similarity score for the pair of items; and transmitting the similar item to a first position on a carousel display of a website that concurrently displays the anchor item on the website. Other embodiments are disclosed.

Systems, apparatus, and methods for providing diversified promotions are discussed herein. Some embodiments may include a system including circuitry configured to provide diversified promotions within an impression or other communication including multiple promotions. For example, promotions may be associated with diversity characteristics to determine the diversity of promotional offerings within an impression and/or within a series of impressions over a period of time sent to a targeted consumer. When an impression is determined to lack diversity based on the diversity characteristics of the promotions, the system may be configured to take corrective action such as by replacing at least one promotion with a replacement promotion that provides greater diversity to the impression.