In general, embodiments of the present invention provide systems, methods and computer readable media configured to use a per-set level optimization of the rank order of promotions to be recommended to a consumer. In some embodiments, machine learning is used offline to generate a predictive diversity model that receives one or more similarity rank features associated with a promotion (e.g., category, price band) as input, and produces an output multiplier to be applied to the promotion's respective associated relevance score (e.g., a relevance score representing a prediction of the promotion's conversion rate without diversity features). At run time, per-set optimization of the ordering of a set of promotions is implemented by adjusting the respective associated relevance scores of the promotions using the diversity model and then re-ordering the set of promotions based on their respective adjusted relevance scores.

The present disclosure is directed to systems and methods for programmatic digital advertisements that are personalized and uniquely targeted to individually-identified consumers via non-personal, but individually accessed devices. The consumer accessing a non-personal device is identified and data cookie pertaining to the user is created and sent to third-party programmatic advertising exchanges for the use in real time bidding, private marketplace deals, or programmatic guaranteed sales. This allows for personalized digital advertisements to be delivered to a specific user accessing a non-personal device.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for enterprise connectivity are described. In one aspect, a method includes the actions of receiving, by a data analysis server and from a web client running on a first device, a request to begin a web session, where the data analysis server is configured to generate queries to a data storage device based on user input to the web client. The actions further include receiving a request to generate a dashboard interface that provides a visualization of a portion of data in the data storage device. The actions further include generating the dashboard interface and a corresponding dashboard file that is viewable outside of the web client. The actions further include transmitting the dashboard file to a second device that includes a data analysis application that is configured to view the dashboard file.

A method and apparatus for selecting treatment for visitors to online enterprise channels are disclosed. The method includes receiving information related to a visitor and a current activity of the visitor on an online enterprise channel. The information is transformed to generate transformed data and a plurality of features is extracted from the transformed data. Using the plurality of features, it is determined whether a treatment when rendered to the visitor is capable of increasing a likelihood of the visitor performing a desired action during a current visit to the online enterprise channel. The treatment is selected and rendered if it is determined that the treatment is capable of increasing the likelihood of the visitor performing the desired action. No treatment is rendered if it is determined that no treatment from among the plurality of treatments is capable of increasing the likelihood of the visitor performing the desired action.

In a computer-implemented method, telematics data collected during one or more time periods by one or more electronic subsystems of a vehicle, and/or by a mobile electronic device of the driver or a passenger, is received. The telematics data includes operational data indicative of how a driver of the vehicle operated the vehicle. The received telematics data is analyzed to identify driving behaviors of the driver during the time period(s). Based at least upon the driving behaviors, a driver profile is generated or modified. Based at least upon the generated or modified driver profile, a suggested vehicle type is identified, at least by determining that the profile meets a set of one or more matching criteria associated with the suggested vehicle type. An indication of the suggested vehicle type is displayed to a user.

Systems and methods are shown for providing private local sponsored content selection and improving intelligence models through distribution among mobile devices. This allows greater data gathering capabilities through the use of the sensors of the mobile devices as well as data stored on data storage components of the mobile devices to create predicted models while offering better opportunities to preserve privacy. Locally stored profiles comprising machine intelligence models may also be used to determine the relevance of the data gathered and in improving an aggregated model for identifying the relevance of data and the selection of sponsored content items. Distributed optimization is used in conjunction with privacy techniques to create the improved machine intelligence models. Publishers may also benefit from the improved privacy by protecting the statistics of type or volume of sponsored content items shown with publisher content.

A method and a device for displaying a commodity advertisement, and a computer-readable storage medium. The method for displaying a commodity advertisement includes: obtaining object attribute information of one or more display objects of a display terminal who view a commodity advertisement, the object attribute information including at least gender information of each display object and display object quantity information corresponding to each gender; determining a first display object according to the obtained object attribute information, and selecting, according to the first display object, a first advertisement from a first category of commodity advertisements for display; and obtaining distance information between at least one display object and a preset target during displaying the first advertisement, and determining, according to the distance information, whether to select a second advertisement from a second category of commodity advertisements for display. The first advertisement and the second advertisement are advertisements of a same commodity.

Systems and methods are disclosed for providing a reservation based subscription service that includes one or more processors that perform operations comprising: receiving reservation information for a subscriber of a reservation-based subscription service, the reservation information comprising a booking date and a reservation date; computing a subscription value for the subscriber based on the reservation information; searching a list of reservation services that are available on the reservation date to identify a first candidate reservation service of a first type that corresponds to the subscription value; computing an addon value based on a difference between a value of the first candidate reservation service and the subscription value; identifying, within the list of reservation services, a second candidate reservation service of a second type that corresponds to the addon value; and generating a candidate composite offering that includes the first candidate reservation service and the second candidate reservation service.

A computer-implemented method for implementing separated attention on like and dislike items for personalized ranking includes performing an element-wise product on a user embedding and a final like item embedding to generate a first vector. The method further includes performing an element-wise product on the user embedding and a final dislike item embedding to generate a second vector. The method further includes computing a probability that the user prefers the like item to the dislike item based on the first and second vectors, and generating one or more item recommendations including one or more electronic images for the user using the probability.

An online system may identify content with which a user has an interest. For example, the online system may determine that a user has an interest in the content based on interaction information indicating that the user interacted with the content. In a particular example, the online system may identify image concepts included in the content based on computer vision techniques that recognize the image concepts. The online system may model probabilities that image concepts will appeal to users. Based on the modeled probabilities, the online system may automatically recommend image concepts for inclusion in candidate images, automatically generate candidate images, or assess candidate images to determine a probability of user interaction with the assessed candidate images.