Methods, systems, and apparatus include computer programs encoded on a computer-readable storage medium, including a method for providing content. A linking is provided of identifiers for users or devices known to a content delivery service. Each identifier is associated with the user or device in a specific context. The linking includes first and second identifiers. A request for content is received that includes either the first or second identifier. Bidders in an exchange are identified that have expressed an interest in bidding on a content delivery opportunity associated with the user or the device. For each bidder, a relative value is determined for a respective bidder for the opportunity to present content to the user or device in association with each identifier known to the bidder. For each bidder, a real-time bid request is generated in the exchange that includes the highest value identifier for submission to a respective bidder.

Techniques train a tree to identify offers to send to a particular customer. Messages that include offers and having attributes are sent to a target user group. Feature measure results from the messages on the target user group, is used with feature measure results for a control user group, to train the tree with branch splits being identified based on maximizing an information gain from the feature measure results for a message/user attribute, where each node within the tree includes target and control distributions for the feature measure. The tree is traversed for a given marketing message/user, drawing randomly from feature measure distributions in the tree to determine whether to send the given marketing message to the user. By drawing randomly from the feature measure distributions, exploration and exploitation of various messages may be performed to minimize ignoring of messages that may have an information gain for particular customers.

Subject innovations are directed towards a platform architecture, system, and special purpose software and hardware that employs a machine learning approach using transactional behavioral events and data about customers to allow a telecommunications marketer to express a set of configurable business rules and constraints, and within a dynamic optimization approach, derive solutions or marketing approaches to optimize delayed key performance indicators. In one embodiment, this is obtained using marketing experiments that seek to learn and influence long term behaviors of customers.

A computer-based method and system are disclosed to facilitate communicating with a visitor to a web-based information resource (e.g., a website or the like), particularly with advertising units directed toward that person after the person's visit to the web-based information resource is over. The method includes: tracking the person's activities on the web-based information resource, receiving instructions from an agent associated with the web-based information resource to communicate with the person whose activities have been tracked, creating the advertising unit with a communication to the person based on the agent's instructions, and causing the advertising unit to be displayed at the same or another web-based information resources, if it support advertising, for example, when that person visits that same or other web-based information resource.

Methods and systems and mobile device interfaces for creating, joining, organizing and managing via mobile devices affinity groups in a cloud computing environment for social and business purposes.

A platform, a method and a cloud data interaction product with customized alerts, fraud alerts,notifications, services, promotions and communication between financial institutions and their clients. The invention is a solution that allows the user to integrate information from several financial institutions, through all channels and for all financial products such as credit and debit cards, checking accounts, savings accounts, insurance policies, loans, investments and others. In addition, it creates a bridge for all channels used by clients, such as mobile devices, ATMs, electronic banking, IVR, POS and others

An online system receives an advertisement request (“ad request”) including an advertisement, targeting criteria identifying characteristics of users eligible to be presented with the advertisement, and one more rules associating weights with characteristics of users. Based on the rules included in the ad request, the online system generates a cluster model that is applied to characteristics of users who do not have characteristics satisfying the targeting criteria in the ad request to generate cluster scores. Users with cluster scores equaling or exceeding a cluster group cutoff score are identified as eligible to be presented with the advertisement in the ad request despite not having characteristics satisfying the targeting criteria in the ad request. Hence, the ad request is eligible for presentation to users having characteristics satisfying the ad request's targeting criteria or having cluster scores equaling or exceeding the cluster group cutoff score.

According to various aspects, a method and system provides a collaborative platform comprising performing a collaborative interactive session for a plurality of members, wherein some or all of the plurality of members interact from different human interaction platforms.

An initial user is selected and social data associated with the user is retrieved. Social contacts within the profile are identified and assessed for association with a product or product type. Social contacts are sorted according to their proximity to the initial user. Target or reference contacts are identified based on product association and proximity.

An advertising apparatus receives requirements for searching documents, acquires, for each of the requirements, a first list that arranges in ascending order document numbers, each of which is associated with a corresponding one of the documents and extracts starting document numbers of the respective requirements of the first list to thereby prepare a second list. Each starting document number totals a count that satisfies a minimum requirement count that represents the number of requirements required for the document to be searched. When a maximum document number among the document numbers belonging to the second list matches another document number, the advertising apparatus retains the other document number in the second list, and when another document number does not match the maximum document number, the advertising apparatus replaces the other document number with any other document number in the first list to which the other document number belongs.