Embodiments of the systems described herein can implement one or more visitor stitching processes. Visitor stitching can include, among other things, one or more processes by which multiple visitors that may appear distinctly independent may be merged into a new single united visitor profile due to the leveraging of one or more unique persistent identifiers.

A method trains a model for providing content items to users of a social networking system. The system generates profile vectors based on user profile information such as demographic data and personal data. The system logs actions performed by users on the social networking system and generates behavior vectors based on the logged actions. The profile vectors and behavior vectors are each associated with a user attribute, e.g., the age or gender of a user. The system generates a difference vector based on a profile vector and a behavior vector. The difference vector is then used as a feature to train the model using machine learning techniques. The trained model may select content items that a target user is most likely to be interested in and interact with.

Examples of systems and methods for wagering on an artist are disclosed. In one example according to aspects of the present disclosure, a computer implemented method for wagering on an artist includes: obtaining, by an electronic exchange of a wagering system server, an initial value for a metric related to the artist from a popularity profiling system server; receiving, by the electronic exchange, a transaction request from a client computer, wherein the transaction request relates to a wager on a future value of the metric related to the artist; generating, by the electronic exchange, a wager metric related to the transaction; and predicting, by a prediction engine of a wagering system server, the future value of the metric related to the artist based on the initial value of the metric and the wager metric.

A third party facilitates exchange of customer data between first and second entities while maintaining customer privacy. Personally identifiable information (PII) and first entity customer attributes of a first set of customers are received from a first entity. PII for a second set of customers is received from a second entity. First and second set common customers are identified using the PII of the first and the second set of customers. Subsequently, a list of third set of customers is sent to the second entity. The list of third set of customers includes the common customers and a plurality of other customers from the second set of customers. Second entity customer attributes are received for each customer in the list of third set of customers. Further, the first entity customer attributes of the common customers and the second entity customer attributes of the common customers are linked.

Methods and systems for intelligently recommending selections for a selector control are disclosed. The method includes receiving a recommendation request from a selector control client, the recommendation request comprising a search string and a unique identifier of a user interacting with a selector control; identifying user identifiers of usernames matching the search string; retrieving machine learning features corresponding to the user identifiers of usernames matching the search string; applying a machine learning model to the retrieved machine learning features to assign weights to the retrieved machine learning features; computing recommendation scores for the user identifiers based on the assigned weights to the retrieved machine learning features; ranking the user identifiers based on the recommendation scores; and forwarding a ranked list of user identifiers to the selector control client for displaying in the selector control for selection by the user interacting with the selector control.

A method including receiving segments of a medical information natural language conversation stream at an artificial intelligence-based health information conversation agent from a user interface; responsive to medical information content of a user profile associated with the conversation stream, defining a desired clinical management outcome objective relevant to health management criteria and related health management data attributes of the user profile; identifying potential therapeutic interventions correlated to advancement of the clinical management outcome objective; selecting a medical intervention from the potential therapeutic interventions correlated to advancement of the outcome objective; presenting in the conversation stream a therapeutic advice conversation stream segment designed to stimulate execution of the medical intervention likely to advance the outcome objective; and presenting to the user in the stream a therapeutic advice conversation stream segment explaining a correlation between the medical intervention likely to advance the outcome objective and achievement of the outcome objective.

A computer-implemented method of matching a customer with a service provider, the method comprising: creating, by a computing device, a profile of a customer having a plurality of categorical values descriptive of or liked by the customer; creating, by the computing device, a profile of a service provider having a plurality of categorical values descriptive of or liked by the service provider; creating, by the computing device, a request by the customer to recommend a service provider, wherein the request includes one or more requested categorical and discrete values; and providing, by the computing device, ranked recommendations of service providers to the customer based on a comparison of the categorical values in the profiles of the customer and the service provider and the requested categorical and discrete values by the customer. A service provider can be a hair stylist.

Examples of techniques for performing a skill gap comparison between a first individual and a second individual (or group) are disclosed. In one example, a computer-implemented method includes receiving first data associated with the first individual and receiving second data associated with the second individual. The method further includes identifying preferences for performing the skill gap comparison and assigning a weight for each of a plurality of elements of the first data and the second data. The method further includes performing the skill gap comparison between the first individual and the second individual by comparing the first data to the second data. The method further includes generating a list of one or more skills for which there is a skill gap between the first individual and the second individual.

A traditional data processing system is configured to process input data either in batch or in real-time. On one hand, a batch data processing system is limiting because the batch data processing often cannot take into account any data received during the batch data processing. On the other hand, a real-time data processing system is limiting because the real-time system often cannot scale. The real-time data processing system is often limited to dealing with primitive data types and/or a small amount of data. Therefore, it is desirable to address the limitations of the batch data processing system and the real-time data processing system by combining the benefits of the batch data processing system and the real-time data processing system into a single data processing system.

A computer extracts from contact records that each include a contact identifier, a group identifier for each group with which the contact has had an interaction, and interaction information that indicates a number of interactions and a timing of a most recent interaction. The contact data records are processed to generate a contact profile record for each contact including group metric values and a corresponding value for each group metric value based on an interaction history of groups the contact has interacted with. An interaction analytics databases stores a set of contact profile records and group profile records for groups that include metric values associated with the group and an interaction history. They are processed with at least thousands of the contact profile records to determine group-contact compatibility factors. A compatibility parameter is generated and communicated for each of at least thousands of contacts based on the group-contact compatibility parameters.