A method is provided that includes receiving, in a server, a request from a service provider, the request including a consumer identification code associated with a consumer, and obtaining a personalized list of universal product codes based on the consumer identification code and a purchase history log in a database. The method also includes providing the personalized list of universal product codes to the service provider, and receiving a tracking pixel indicative that the consumer has interacted with a consumer payload, wherein the consumer payload is associated with at least one product from the personalized list of universal product codes. A system and a non-transitory, computer-readable medium storing instructions which cause the system to perform the above method are also disclosed.

This invention teaches how one can identify user interests based upon portions of content i.e. at a finer level of granularity than known until now. Existing computer technology could identify that a user was interested in animals if he viewed a page about animals. The instant invention allows a user to select/generate/reference/isolate a portion of content, and s/he can do this without having to install additional software to his/her browser/device. Thus, we can now know if a specific user is interested in cats, and another in dogs based upon the content portions s/he chose to reference/interact with. A profile of a user's interests can be developed across a multitude of documents. This profile of the user's interests can then be leveraged for commerce such as: better, targeted, contextual advertising; developing analytics; and far superior insights into user interests can be obtained.

Disclosed are systems, methods, and non-transitory computer-readable media for differential bid generation using machine learning. A bid management system generates an input based on features of a content item and. The bid management system uses the input to determine acceptance probability score distributions for a set of candidate users. The bid management system uses the acceptance probability score distributions along with user attributes describing the set of candidate users along with campaign parameters to determine a subset of the candidate users to receive an offer to view the content item along with bid values to offer to each candidate user.

Vehicle manufacturers may leverage one vehicle of a household to gain intelligence to determine whether a new vehicle may be purchased or an existing vehicle may be replaced for the household. Techniques include identifying a home geofence space that identifies the household at the household address for the vehicle. The sensor data from the vehicle can be used to identify other vehicles within the home geofence space. When other vehicles are identified that match appropriate criteria, the other vehicles may be associated with the household. Further observation of the other vehicles and the behavior of the members of the household can be used to identify when an existing vehicle of the household may be replaced and/or a new vehicle may be purchased. Upon determining that a new or replacement vehicle may be purchased, marketing materials may be provided to the household to aid the household with purchasing the new vehicle.

This application relates to apparatus and methods for automatically determining and providing carousels specifically curated for a user. In some examples, a computing device obtains user transaction data identifying in-store and/or online transactions, and user engagement data identifying user interactions with items and carousels from user's prior sessions. The computing device determines a sequential order for presentation of carousels with a set of item recommendations. For example, the computing device scores each potential carousel based on prior user interactions and transactions with items and carousels. The carousels are then ranked and subsequently presented to the user based on their corresponding scores.

In one aspect, a computerized method for implementing entity interaction history signatures includes the step of providing a set of entities in an online network. The method includes the step of comparing a first entity of the set of entities with a second entity of the set of entities using a first entity interaction history signature of the first entity and second entity interaction history signature of the second entity. The method includes the step of based on the comparison of the first entity with the second entity computing a similarity measure. The method includes the step of aggregating a set of entity interaction history signatures for the set of entities to create a group signature.

A method for matching a user to a service provider, comprising: obtaining a user profile for a user capturing at least one of: a sought service type, service quality, service speed, a risk niche, a demographic niche, a socio-economic niche, a quote acceptance likelihood, a binding likelihood, and an expected life time value; obtaining multiple service provider profiles capturing at least one of: an offered service type, service quality, service speed, a target risk niche, a target demographic niche, a target socio-economic niche, a quote acceptance threshold, a binding threshold, and an expected user life time value threshold; matching the user with at least one service provider by fitting the respective profiles; presenting the matched service provider to the user; receiving a confirmation; establishing a channel between the user and the matched service provider; and providing at least one aspect of the user profile to the matched service provider.

The Portable Universal Profile Apparatuses, Processes and Systems (“PUP”) transform embed code snippet, embedded reference code, RSS feed identifier, multires values, multires map, handle record, inputs via PUP components into autolinker parameters (e.g., DOI, menu specification ID, hierarchical menu tag), interlinking metrics, web logs, tracking metrics, PUP menus, PUP transactions outputs. The PUP, provides interactive, responsive and efficient portable universal profile for creating universal portable IDs for individuals, entities, and/or systems. In one embodiment, the PUP allows people to package web links to the information of interest to them in a responsive tag or PUP-interface. For example, a user may create a personal widget comprised of links to the content, events and products they want to promote and share. In one embodiment, this personal widget may be an easy-to-use application for online self-publishing and self-distribution, complete with available user metrics. In a further embodiment, the PUP may let a user know every time a friend looks at their widget or clicks a link In this way, users can get a better understanding of common interests and get feedback from friends on what they may be most interested in. The personal widget may be portable and posted ubiquitously across the Web, and/or it may be posted within particular technical environments taking advantage of particular functionality available in those environments (such as social networking sites like Facebook.com, MySpace.com, LinkedIn.com, etc.). In some embodiments, a PUP-I interacts with the environment in which it is posted/hosted or published. In some such embodiments, the PUP-I may be configured to obtain and/or supply data associated with the user, updating and reconciling information between and among various environments (e.g., coordinating a user's MySpace profile with their Facebook profile).

Systems and methods related to a social syndicate platform for buyers and sellers on a social network includes aggregating requests for goods or services by individual members of a social network. Individual members may send buyer-sourced requests for deals to business members of the social network with parameters restricting which businesses may be considered in the request. Business members may send discounted offers for goods and services including restrictions on which individuals may receive the offer. A computing system may facilitate deals between businesses and individuals based on financial health considerations and make offer recommendations to business and deal recommendations to individuals.

A method for generating a singularity recommendation includes receiving structured and unstructured data for a user, where the structured and unstructured data for the user provide a first context for generating a singularity recommendation. The method, responsive to identifying a location for the user, determines ecosystem data based on the location for the user, where the ecosystem data provides a second context for generating the singularity recommendation. The method determines environmental data based on the location for the user, where the environmental data provides a second context for generating the singularity recommendation. The method generates the singularity recommendation based on the first context, the second context, and the third context directed to the user. The method displays the singularity recommendation in a user interface on a client device associated with the user.