Bank of America Corporation

Charles F Pigg

Somnath Choudhuri

Matthew D Hoke

Sethu Iyer

Daniel Bodalski

Paul Martin Mattison, Sr

Roberto Jose Dominguez

Tommi Levi

Paul Cooley

David Barnhardt

Methods, systems, and computer-readable media for determining whether a check may be cashed at an automated teller machine (ATM) are provided. The ATM may capture check image data from the face of the check and the ATM may transmit the data to a check cashing computing platform. The check cashing computing platform may determine whether the account on which the check is drawn is an account of a first financial institution associated with the ATM, or the account is an account of a second financial institution. A first or second set of rules may be applied to the check based on this determination, to determine an overall check cashing risk score. A determination is then made, based on the overall check cashing risk score, as to whether the check may be cashed or the request to cash the check may be denied.

Transaction decisioning by an automated device

Methods, systems, and computer-readable media for determining whether a check may be cashed at an automated teller machine (ATM) are provided. A user may request to cash a check at an ATM and check image data may be transmitted to a return deposit item computing platform. The computing platform may identify an account number of the account on which the check is drawn. Transaction data associated with the account may be retrieved by the computing platform and a number of occurrences of returned deposit items may be identified. The number of occurrences may be used to determine whether the check should be cashed.

A multi-stage filtering process and system for fraud detection is disclosed. The process includes one or more preliminary filtration stages followed by one or more additional filtration stages that provide for enhanced screening for fraudulent activity. In one such embodiment the preliminary filtration provides for evaluating financial transactions based on financial transaction attribute data and secondary filtration provides for further evaluating the financial transactions based on a customer's account event data. Over a plurality of transactions, a portion of the transactions are cleared for processing (e.g., deemed not likely fraudulent or of too low value to continue processing) after each filtration stage. As such, acceptable transactions are not unnecessarily scrutinized. In specific embodiments, filtration is based on financial transaction data and account event data.

Multi-stage filtering for fraud detection with account event data filters

A multi-stage filtering process and system for fraud detection is disclosed. The process includes one or more preliminary filtration stages followed by one or more additional filtration stages that may include velocity filters that provide for enhanced screening for fraudulent activity. Over a plurality of transactions, a portion of the transactions are cleared for processing (e.g., deemed not likely fraudulent or of too low value to continue processing) after each filtration stage. As such, acceptable transactions are not unnecessarily scrutinized.

Multi-stage filtering for fraud detection with velocity filters

A multi-stage filtering process and system for fraud detection is disclosed. The multi-stage filtering process allows for the ability to dynamically increase/decrease server capacity, as well as application capacity to support fraud detection activities. The system monitors the queues of the transactions being made using various channels, and responds by adjusting the server and application resources needed for performing pre-filtering on the transactions in the queues. The invention allows for the fraud detection systems to maintain the capacity necessary to examine, at some level, if one or more of the transactions being processed by a financial institution are potentially fraudulent. The capacity can be changed during times of high and low volumes, thus allowing the allocation of resources based on transaction volume, which reduces the computing, energy, labor, etc. costs associated with fraud detection systems without losing the ability to detect almost all of the fraudulent transactions occurring.

Capacity customization for fraud filtering

A multi-stage filtering process and system for fraud detection is disclosed. The process includes one or more preliminary filtration stages followed by one or more additional filtration stages that may include customer history filters that provide for enhanced screening for fraudulent activity. Over a plurality of transactions, a portion of the transactions are cleared for processing (e.g., deemed not likely fraudulent or of too low value to continue processing) after each filtration stage. As such, acceptable transactions are not unnecessarily scrutinized.

Multi-stage filtering for fraud detection with customer history filters

Systems and methods are illustrated for providing enhanced fraud protection. Aspects of the fraud protection system may be implemented by a filter that may be configured to detect fraud in a transaction between a financial institution and a customer. An input device may receive data that corresponds to a transaction between a financial institution and a customer, such as a transfer of money. A data store may store information relating to the transaction that includes the serial number and dollar amount of the transfer of money. When the filter detects fraud, an output device may output an alert resulting in zero false positives. The filter may also include a module that is configured to compare the data that is received by an input device to data that is stored in the data store. Oftentimes, the data in the data store may be information relating to past fraud protection.

Growing community of inventors

Plano, TX, United States of America

Charles F Pigg