Abstract: A heuristic engine includes capabilities to collect an unstructured data set, for example including question and answer sets from prior customer interactions, and predict future questions based on a current customer context. Such heuristic algorithms may learn from past data transactions and appropriate correlations with events and available data. By improving the heuristic algorithm with growing sets of question and answer interactions, the accuracy of question and answer set predictions may improve over time, allowing improved customer service and understanding of customer interaction outcomes.

Abstract: Systems and methods are described for Distification of 3D imagery. A computing device may obtain a three dimensional (3D) image that includes rules defining a 3D point cloud used to generate a two dimensional (2D) image matrix. The 2D image matrix may include 2D matrix point(s) mapped to the 3D image, where each 2D matrix point can be associated with a horizontal coordinate and a vertical coordinate. The computing device can generate an output feature vector that includes, for at least one of the 2D matrix points, the horizontal coordinate and the vertical coordinate of the 2D matrix point, and a depth coordinate of a 3D point in the 3D point cloud of the 3D image. The 3D point can have a nearest horizontal and vertical coordinate pair that corresponds to the horizontal and vertical coordinates of the at least one 2D matrix point.

Abstract: A method of automating a fraud classification process includes generating or updating fraud classification rules, at least by training a machine learning program using fraud classifications of a plurality of financial accounts and financial transaction data associated with those accounts. The method also includes retrieving first financial transaction data associated with a first financial account, and selecting, by applying the fraud classification rules to the first financial transaction data, a first fraud classification. The first fraud classification may be selected from among a plurality of predetermined fraud classifications. The method also includes causing an indication of the first fraud classification to be displayed to one or more people via one or more respective computing device user interfaces, the indication further specifying at least the first financial account.

Abstract: A heuristic engine includes capabilities to collect an unstructured data set and a set of question and answer sets that allow prediction of a subsequent question by a customer. By improving prediction of a subsequent customer question the heuristic engine may improve the efficiency of customer service interactions. The heuristic engine may improve and learn by providing actual interaction sets with correlations associated with the predicted outcomes.

Abstract: A heuristic cross-selling recommendation engine includes capabilities to collect an unstructured data set and a current business context to suggest marketing actions. By providing a heuristic algorithm and executing the algorithm within the engine with the data set allows determination of predicted future contexts and optimal marketing actions. Such heuristic algorithms may learn from past marketing transactions and appropriate correlations with events and available data.

Abstract: In a computer-implemented method of reducing false positives among geolocation-based fraud alerts issued in connection with card-present financial transactions, it may be determined that a fraud alert exists for a card-present financial transaction. A first geographic location, at which information associated with a debit or credit card account was obtained by swiping or inserting a card, may be determined, along with a time of the transaction. Based upon geolocation data indicating one or more geographic locations of the authorized cardholder, it may be determined that the authorized cardholder was at a second geographic location at the time of the financial transaction. If the second geographic location corresponds to the first geographic location, the fraud alert may be marked as a false positive, such that no fraud alert is sent to the authorized cardholder in connection with the financial transaction.

Abstract: In a computer-implemented method of reducing financial transaction disputes caused by introductory offers expiring, an introductory offer that is associated with customer disputes or complaints after the introductory offer has expired may be identified. Financial transaction activity associated with customers may be received, and customers having transaction activity associated with the introductory offer may be identified. An electronic notification indicating that the customers have accepted or are using the introductory offer may be generated, and transmitted to customer mobile devices to facilitate customer review and cancellation of the introductory offer prior to expiration.

Abstract: A heuristic business impact engine includes capabilities to collect an unstructured data set and a current business context to predict future business outcomes based on past business activity. Providing a heuristic algorithm, executing the algorithm within the engine with the data set and the context may allow determination of predicted future business action. Such heuristic algorithms may learn from past data transactions and appropriate correlations with events and available data.

Abstract: A heuristic engine includes capabilities to collect an unstructured data set and authenticate a user's identity. By providing a heuristic algorithm with unstructured data, such as question and answer sets related to a user's activities in the past, a correlation factor can be calculated with a current context. Authenticating users using heuristic algorithms ensures precision and predictability of authentication decisions. Such heuristic algorithms may learn from each interaction and improve the accuracy of authentication decisions in the future.

Abstract: Systems and methods are described for generating an image-based prediction model, where a computing device may obtain a set of 3D images from a 3D image data source. Each of the 3D images can have 3D point cloud data and a Distification technique can be applied to the 3D point cloud data of each 3D image to generate output feature vector(s). The output feature vector(s) may then be used to train and generate the image-based prediction model.

Abstract: A method of detecting whether electronic fraud alerts are false positives includes receiving data detailing a financial transaction, inputting the data into a rules-based engine that determines whether to generate an electronic fraud alert for the financial transaction based upon the data, and, when an electronic fraud alert is generated, inputting the data into a machine learning program trained to identify one or more facts indicated by the data. The method may also include determining whether the identified facts can be verified by customer data and, in response to determining that the facts can be verified, retrieving or receiving first customer data. The method may further include verifying that the electronic fraud alert is not a false positive based upon analysis of the first customer data, and transmitting the verified electronic fraud alert to a mobile device of the customer to alert the customer to fraudulent activity.

Abstract: A method of identifying a merchant computer terminal warranting a chargeback includes identifying a merchant computer terminal associated with a fraudulent financial transaction, and receiving information associated with the merchant computer terminal. The information may include an actual configuration, parameters, and/or specifications associated with the merchant computer terminal. The method also includes receiving up-to-date dispute rules associated with chargebacks, and analyzing the dispute rules to determine merchant computer terminal requirements. The method further includes comparing the terminal requirements with the information associated with the merchant computer terminal to identify whether the merchant computer terminal is compliant with the dispute rules.

Abstract: A heuristic engine includes capabilities to collect an unstructured data set, such as a agent sales transaction record, and generate an agent training suggestion for subsequent action. Providing the heuristic engine with relevant data sets and a current context may allow determination of predicted future customer contexts and subsequent actions. The heuristic engine may learn from past data transactions and appropriate correlations with events and available data.

Abstract: In a computer-implemented method of pre-empting fraud disputes caused by billing aliases or unrecognized merchant billing names, an indication that a credit card financial transaction is unrecognizable by the card owner may be received. A billing alias for a merchant associated with the unrecognizable transaction may be determined, where the billing alias is named on a credit card statement as billing merchant. A brick and mortar name that the merchant associated with the billing alias is doing business as may be determined, and an electronic notification indicating the brick and mortar name of the merchant may be generated. The electronic notification may be transmitted to a mobile device of the card owner over a wireless communication channel for card owner review or approval to facilitate preventing financial disputes caused by unrecognized or unfamiliar billing aliases on credit card or other financial statements.

Abstract: Techniques are disclosed to provide customized loans on a per-user basis. With user permission or affirmative consent, user data may be monitored for several users, which may be used to calculate initial loan specifics such as a loan rate and term based upon a portion of this user input data. The user data may include demographic data, behavioral data, or other data indicative of a user's future potential earnings or other relevant information that may be analyzed to determine, for that specific user, the current likelihood that the user will default on the loan and a future likelihood of default. When this future statistical likelihood is determined, the initial loan specific may be further modified and/or a targeted notification may be sent indicating these customized loan specifics.

Abstract: Techniques are disclosed to provide customized loans on a per-user basis. With user permission or affirmative consent, user data may be monitored for several users, which may be used to calculate initial loan specifics such as a loan rate and term based upon a portion of this user input data. The user data may include demographic data, behavioral data, or other data indicative of a user's future potential earnings or other relevant information that may be analyzed to determine, for that specific user, the current likelihood that the user will default on the loan and a future likelihood of default. When this future statistical likelihood is determined, the initial loan specific may be further modified and/or a targeted notification may be sent indicating these customized loan specifics.

Abstract: Techniques are disclosed utilizing cognitive computing to improve banking experiences. A user's financial account(s) and location may be monitored to determine that a user is near an asset that is listed for sale. The techniques disclosed include receiving multiple locations for a user's mobile device over a period of time and determining when the mobile device is within a predetermined threshold distance of the asset listed for sale. The techniques include building a financial profile for the user based upon financial information for the user. The financial profile may be used to determine a loan to offer to the user for purchasing the asset listed for sale based upon the financial profile.

Abstract: A method of identifying a merchant computer terminal warranting a chargeback includes identifying a merchant computer terminal associated with a fraudulent financial transaction, and receiving information associated with the merchant computer terminal. The information may include an actual configuration, parameters, and/or specifications associated with the merchant computer terminal. The method also includes receiving up-to-date dispute rules associated with chargebacks, and analyzing the dispute rules to determine merchant computer terminal requirements. The method further includes comparing the terminal requirements with the information associated with the merchant computer terminal to identify whether the merchant computer terminal is compliant with the dispute rules.

Abstract: Techniques are disclosed utilizing cognitive computing to improve banking experiences. A user's financial account(s) may be monitored to predict when a surplus of funds is unnecessarily present and for how long this will likely be the case. Once this is determined, techniques include automatically drafting funds from the account to another account having a higher interest rate where the funds may accrue more interest. The techniques also include predicting when an overdraft may occur and taking appropriate action when such a prediction is made. Predictions may be based upon different weighted inputs used in accordance with a predictive modeling system, which may attempt to predict for a particular user, location, and retailer, whether the user will spend an anticipated amount in excess of the user's current balance. If so, passive (e.g., notifications) and active (e.g., transferring cover funds) actions may be performed.

Abstract: A heuristic engine includes capabilities to collect an unstructured data set and a current business context. Providing a heuristic algorithm, executing within the engine, with the data set and the context may allow determination of predicted future contexts and subsequent actions that refine and improve the quality of service provided to a customer. Such heuristic algorithms may learn from past data transactions and appropriate correlations with events and available data.