Abstract: Disclosed herein is system, method and architecture to process information received in electronic messages, including identifying events in the lives of users from the information contained in one or more such electronic messages.

Abstract: A method for pairing wearable computing device activity data with additional data includes: storing a plurality of activity profiles, wherein each activity profile includes data related to activity of a wearable computing device including at least a device identifier and one or more activity data entries; storing a plurality of transaction data entries, wherein each transaction data entry includes data related to an electronic transaction including at least a primary account number and additional transaction data; receiving pairing data, wherein the pairing data includes at least a specific device identifier and a specific primary account number; identifying a specific activity profile where the included device identifier corresponds to the specific device identifier; identifying one or more transaction data entries where the included primary account number corresponds to the specific primary account number; and updating the identified specific activity profile to include at least the specific primary account

Abstract: A cross-device messaging integration capability is disclosed, which allows a user using a first device to indicate, using a first user computing device, an intent to perform one or more messaging actions at one or more second user computing device(s). The first and second devices may be different devices. The user may receive a reminder or other notification of the user's intent at the second device(s).

Abstract: A method for establishing trigger events for wearable computing device activity includes: receiving a trigger event submission, the trigger event submission including at least an activity unit type, one or more activity unit values, and an application identifier associated with an application program corresponding to a wearable computing device; storing an activity unit profile, wherein the activity unit profile includes at least the application identifier and the activity unit type; storing a trigger profile for each activity unit value of the one or more activity unit values, wherein each trigger profile includes at least the application identifier and the respective activity unit value; and electronically transmitting a confirmation notification indicative of confirmation of storage of the trigger profile for each activity unit value to the computing device.

Abstract: A method for distributing content to a mobile communication device includes: storing a plurality of content profiles, wherein each content profile includes at least a content data file and associated trigger data; receiving an activity notification, wherein the activity notification includes at least trigger data associated with activity data corresponding to a wearable computing device interfaced with the mobile communication device; identifying one or more content profiles based on the included associated trigger data and the trigger data included in the activity notification; generating a data signal superimposed with at least the content data file included in the identified one or more content profiles; and electronically transmitting the generated data signal to the mobile communication device.

Abstract: A method for establishing trigger events for wearable computing device activity includes: receiving a trigger event submission, the trigger event submission including at least an activity unit type, one or more activity unit values, and an application identifier associated with an application program corresponding to a wearable computing device; storing an activity unit profile, wherein the activity unit profile includes at least the application identifier and the activity unit type; storing a trigger profile for each activity unit value of the one or more activity unit values, wherein each trigger profile includes at least the application identifier and the respective activity unit value; and electronically transmitting a confirmation notification indicative of confirmation of storage of the trigger profile for each activity unit value to the computing device.

Abstract: A method for pairing wearable computing device activity data with additional data includes: storing a plurality of activity profiles, wherein each activity profile includes data related to activity of a wearable computing device including at least a device identifier and one or more activity data entries; storing a plurality of transaction data entries, wherein each transaction data entry includes data related to an electronic transaction including at least a primary account number and additional transaction data; receiving pairing data, wherein the pairing data includes at least a specific device identifier and a specific primary account number; identifying a specific activity profile where the included device identifier corresponds to the specific device identifier; identifying one or more transaction data entries where the included primary account number corresponds to the specific primary account number; and updating the identified specific activity profile to include at least the specific primary account

Abstract: The disclosure herein concerns facilitating a transaction for a user, storing information about the nature of the transaction on a financial institution server, generating a stop targeting cookie based on the nature of the transaction, and placing the stop targeting cookie on a user's browser. The disclosure also concerns utilizing an electronic data structure representing the content of a transaction by a user of an electronic commerce site from a financial institution server that facilitated the transaction. The ad targeting server compares the transaction content information in the electronic data structure to the re-targeting cookie, and if the at least one re-targeting cookie matches the transaction information, the ad targeting server at least one of deletes, updates, and replaces the re-targeting cookie.

Abstract: A search engine determines a set of other images that are similar to a user-selected image, and presents those other images to the user. In determining whether two images are sufficiently similar to each other to merit presentation of one, the search engine determines a Euclidean distance between separate feature vectors that are associated with each of the images. Each such vector indicates diverse types of information that is known about the associated image. The types of information included within such a vector may include attributes that reflect visual characteristics that are visible in an image, verbal tags that have been associated with the image users in a community of users, concepts derived from those tags, coordinates that reflect a geographic location at which a camera that produced the image was when the camera produced the image, and concepts related to groups with which the image is associated.

Abstract: A card includes a sensor system for fraud detection. A method of fraud detection includes flagging suspicious activity on a transaction card and prompting a user to take a self-image or a voice recording with the credit card.

Abstract: Disclosed herein is a method for providing an offer which includes selecting at least one offer for presentation by applying at least one rule dictated by a merchant to a set of offers, applying at least one rule dictated by a financial institution to the offers, and applying a filter to identify offers with the highest likelihood of being accepted by the user. The selected offer is then presented to the user. An authorization request from a merchant for a user transaction is received by a remote computer and analyzed to determine one or more categories or sub-categories of the merchant or item in the transaction. The system then determines whether the selected offer is for a merchant or item in a related but different category from the one for which the authorization request was received, and if it is, the system reminds the user of the selected offer.

Abstract: A cross-device messaging integration capability is disclosed, which allows a user using a first device to indicate, using a first user computing device, an intent to perform one or more messaging actions at one or more second user computing device(s). The first and second devices may be different devices. The user may receive a reminder or other notification of the user's intent at the second device(s).

Abstract: Disclosed herein is system, method and architecture to process information received in electronic messages, including identifying events in the lives of users from the information contained in one or more such electronic messages.

Abstract: Disclosed herein is a method for identifying a member of a group with particular demographic characteristics. The method involves identifying purchasing behaviors of members of a group with particular demographic characteristics via market research, gathering transaction data from a financial account of a user at a financial institution for processing transactions of the user with the multiple of merchants, using the market research to set prior probabilities that a user is a member of the group in a Bayesian belief network, analyzing the transaction data of the user via a Bayesian belief network to determine whether the transaction data of the user indicates that the user is an individual member of the group with the particular demographic characteristics, and presenting to the user at least one of an offer and a savings opportunity from a merchant seeking to contact members of the group with the particular demographic characteristics.

Abstract: A system and method of targeting users with a reward, offer, or incentive may include selecting at least one reward, offer, or incentive to present to a user by applying at least one rule, restriction, or filter dictated by a merchant to the set to be provided to the user, applying at least one rule, restriction, or filter dictated by a financial institution to the set, and applying a filter to the set to obtain those rewards, offers, or incentives with the highest likelihood of being accepted by the user. At least one parameter of the at least one reward, offer, or incentive is adjusted prior to presentation to the user based on a spending trajectory, user propensity model, user profile information or segmentation criteria, or campaign goal.

Abstract: Disclosed herein is a method for a merchant to gain information about the purchasing characteristics of a group with which the merchant wishes to interact. Merchants wishing to target group members are not able to specifically identify members of the group through depersonalized transaction data available from financial institutions. Group members are therefore identified through a traditional method: market research. The method also includes noting the purchasing behavior of group members, including providers of goods and services to group members, merchants not patronized by members of the group, and demographic characteristics of the group. An example of such a group is the so-called “millennials”. The identification of group members may be validated through test runs of financial data and fine-tuned to ensure correct identification of group members.

Abstract: A television programming recommender combines the explicit viewing preferences, i.e. user specified preferences, of viewers with their television viewing behavior (implicit preferences) to generate program recommendations. The explicit viewing preferences are utilized to generate an explicit recommendation score, E, for an upcoming television program. The implicit viewing preferences are utilized to generate an implicit recommendation score, I, for the program. A combined recommendation score, C, is computed based on the explicit and implicit scores, E and I. The combined recommendation score, C, can be computed using a weighted linear mapping.

Abstract: Techniques are described herein for generating a deal score to indicate a relative value of an offer for a commerce element. In one example, the deal score for a particular offer is based on a difference between a discounted price specified by the particular offer and an average of discounted price(s) specified by other offer(s). If the difference reaches a threshold, then a relatively high deal score is generated. Otherwise, a relatively low deal score is generated. In another example, the deal score is based on a difference between an intermediate value and the discounted price specified by the present offer. The intermediate value may be provided by combining discounted price(s) specified by other offer(s) and the non-discounted price of the commerce element being offered. If the difference reaches a threshold, then a relatively high deal score is generated. Otherwise, a relatively low deal score is generated.

Abstract: Techniques are described herein for providing discounted offers for goods and/or services. In one example, the discounted offer may specify a variable discount. In an aspect of this example, an amount of the variable discount may decrease for each customer or group thereof who accepts the offer. In accordance with this aspect, customer(s) who accept the offer earlier than other customers may be given a greater discount. In another aspect, the amount of the discount may vary for successive predetermined time intervals. For instance, the amount of the variable discount may be greater for customer(s) who accept the offer during a predetermined time interval that occurs earlier than another predetermined time interval. Accordingly, the amount of the discount may decrease for temporally successive predetermined time intervals. In both aspects, once a specified number of customers accept the discounted offer, the discounted offer may thereafter specify a fixed discount.

Abstract: Exemplary methods and apparatuses are disclosed that may be used to provide or otherwise support extraction of objects and facets from one or more extraction corpora and ranking of said facets using multiple ranking corpora.