Abstract: A method of reducing a future amount of electronic fraud alerts includes receiving data detailing a financial transaction, inputting the data into a rules-based engine that generates an electronic fraud alert, transmitting the alert to a mobile device of a customer, and receiving from the mobile device customer feedback indicating that the alert was a false positive or otherwise erroneous. The method also includes inputting the data detailing the financial transaction into a machine learning program trained to (i) determine a reason why the false positive was generated, and (ii) then modify the rules-based engine to account for the reason why the false positive was generated, and to no longer generate electronic fraud alerts based upon (a) fact patterns similar to fact patterns of the financial transaction, or (b) data similar to the data detailing the financial transaction, to facilitate reducing an amount of future false positive fraud alerts.

Abstract: A heuristic money laundering detection engine includes capabilities to collect an unstructured data set, such as a transaction record, and detect indications of money laundering activity. By detecting money laundering activity and feeding back indications of money laundering transactions, the heuristic algorithm may continue to learn and improve detection accuracy. Such indications may include correlations to sets of transaction activity among a number of financial accounts and past indications of money laundering activity. Indications of money laundering may allow generation of audit reports for reporting to regulatory authorities.

Abstract: A heuristic engine includes capabilities to collect an unstructured data set and detect instances of transaction fraud in a financial account. By providing a heuristic algorithm with unstructured transaction sets and indications of particular instances of transactions that correlate with past fraudulent activity allows prevention of future occurrences of fraud. Such heuristic algorithms may learn from past indications of fraudulent activity and improve accuracy of detection of future fraud detections.

Abstract: A method of reducing a future amount of electronic fraud alerts includes receiving data detailing a financial transaction, inputting the data into a rules-based engine that generates an electronic fraud alert, transmitting the alert to a mobile device of a customer, and receiving from the mobile device customer feedback indicating that the alert was a false positive or otherwise erroneous. The method also includes inputting the data detailing the financial transaction into a machine learning program trained to (i) determine a reason why the false positive was generated, and (ii) then modify the rules-based engine to account for the reason why the false positive was generated, and to no longer generate electronic fraud alerts based upon (a) fact patterns similar to fact patterns of the financial transaction, or (b) data similar to the data detailing the financial transaction, to facilitate reducing an amount of future false positive fraud alerts.

Abstract: A heuristic money laundering detection engine includes capabilities to collect an unstructured data set, such as a transaction record, and detect indications of money laundering activity. By detecting money laundering activity and feeding back indications of money laundering transactions, the heuristic algorithm may continue to learn and improve detection accuracy. Such indications may include correlations to sets of transaction activity among a number of financial accounts and past indications of money laundering activity. Indications of money laundering may allow generation of audit reports for reporting to regulatory authorities.

Abstract: A heuristic engine includes capabilities to collect an unstructured data set and detect instances of transaction fraud in a financial account. By providing a heuristic algorithm with unstructured transaction sets and indications of particular instances of transactions that correlate with past fraudulent activity allows prevention of future occurrences of fraud. Such heuristic algorithms may learn from past indications of fraudulent activity and improve accuracy of detection of future fraud detections.

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 heuristic engine includes capabilities to collect an unstructured data set and a current business context to calculate a credit worthiness score. Providing a heuristic algorithm, executing within the engine, with the data set and the context may allow determination of predicted future contexts and recommend subsequent actions, such as assessing a credit risk of a customer transaction and reducing the risk of customer transactions by processing the available data. Such heuristic algorithms may learn from past data transactions and appropriate correlations with events and available data.

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 heuristic engine includes capabilities to collect an unstructured data set and a current business context to calculate a credit worthiness score. Providing a heuristic algorithm, executing within the engine, with the data set and the context may allow determination of predicted future contexts and recommend subsequent actions, such as assessing a credit risk of a customer transaction and reducing the risk of customer transactions by processing the available data. Such heuristic algorithms may learn from past data transactions and appropriate correlations with events and available data.

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: In a computer-implemented method of facilitating detection of document-related fraud, fraudulent document detection rules may be generated or updated by training a machine learning program using image data corresponding to physical documents, and fraud determinations corresponding to the documents. The documents and fraudulent document detection rules may correspond to a first type of document. Image data corresponding to an image of one of the physical documents may be received, where the physical document corresponds to the first type of document. By applying the fraudulent document detection rules to the image data, it may be determined that the physical document is, or may be, fraudulent. An indication of whether the physical document is, or may be, fraudulent may be displayed to one or more people via one or more respective computing device user interfaces.

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 reducing a future amount of electronic fraud alerts includes receiving data detailing a financial transaction, inputting the data into a rules-based engine that generates an electronic fraud alert, transmitting the alert to a mobile device of a customer, and receiving from the mobile device customer feedback indicating that the alert was a false positive or otherwise erroneous. The method also includes inputting the data detailing the financial transaction into a machine learning program trained to (i) determine a reason why the false positive was generated, and (ii) then modify the rules-based engine to account for the reason why the false positive was generated, and to no longer generate electronic fraud alerts based upon (a) fact patterns similar to fact patterns of the financial transaction, or (b) data similar to the data detailing the financial transaction, to facilitate reducing an amount of future false positive fraud alerts.

Abstract: In a computer-implemented method of using customer data to determine that geolocation-based fraud alerts are false positives, it may be determined that an electronic fraud alert is a geolocation-based alert generated based upon an unexpected or abnormal transaction location. In response, customer data may be obtained from two or more sources via radio frequency links. It may then be determined that the customer data from the sources indicates that a customer is traveling. In response, it may be determined that a customer location indicated by the customer data corresponds to the transaction location. In response to determining that the customer location corresponds to the transaction location, the electronic fraud alert may be marked as a false positive, and the electronic fraud alert may be prevented from being transmitted to a mobile device of the customer, in order to reduce an amount of false positives that are transmitted to customers.

Abstract: In a computer-implemented method of facilitating detection of document-related fraud, fraudulent document detection rules may be generated or updated by training a machine learning program using image data corresponding to physical documents, and fraud determinations corresponding to the documents. The documents and fraudulent document detection rules may correspond to a first type of document. Image data corresponding to an image of one of the physical documents may be received, where the physical document corresponds to the first type of document. By applying the fraudulent document detection rules to the image data, it may be determined that the physical document is, or may be, fraudulent. An indication of whether the physical document is, or may be, fraudulent may be displayed to one or more people via one or more respective computing device user interfaces.

Abstract: A heuristic engine includes capabilities to collect an unstructured data set, including document image data and correlate the image data with known valid data to detect document fraud. Notifications of fraud detection may include particular signature images, or characteristics of a document image. By feeding back indications of document fraud with correlations to past instances of fraud into the heuristic algorithm, the algorithm may learn and improve in fraud detection accuracy.

Abstract: Techniques are disclosed utilizing cognitive computing to improve commercial communications from vendors to users. A user's financial account(s) and location may be monitored to determine when a user is within a threshold distance of a vendor. If the user is within the threshold distance the methods and systems disclosed may determine which targeted commercial communications to transmit to the user based upon a shopping profile for the user. The shopping profile may include a dataset indicative of the shopping habits of the user.

Abstract: A method of reducing a future amount of electronic fraud alerts includes receiving data detailing a financial transaction, inputting the data into a rules-based engine that generates an electronic fraud alert, transmitting the alert to a mobile device of a customer, and receiving from the mobile device customer feedback indicating that the alert was a false positive or otherwise erroneous. The method also includes inputting the data detailing the financial transaction into a machine learning program trained to (i) determine a reason why the false positive was generated, and (ii) then modify the rules-based engine to account for the reason why the false positive was generated, and to no longer generate electronic fraud alerts based upon (a) fact patterns similar to fact patterns of the financial transaction, or (b) data similar to the data detailing the financial transaction, to facilitate reducing an amount of future false positive fraud alerts.

Abstract: In a computer-implemented method of using customer data to determine that geolocation-based fraud alerts are false positives, it may be determined that an electronic fraud alert is a geolocation-based alert generated based upon an unexpected or abnormal transaction location. In response, customer data may be obtained from two or more sources via radio frequency links. It may then be determined that the customer data from the sources indicates that a customer is traveling. In response, it may be determined that a customer location indicated by the customer data corresponds to the transaction location. In response to determining that the customer location corresponds to the transaction location, the electronic fraud alert may be marked as a false positive, and the electronic fraud alert may be prevented from being transmitted to a mobile device of the customer, in order to reduce an amount of false positives that are transmitted to customers.