Bank of America Corporation

Jpmorgan Chase Bank, N.a.

Somnath Choudhuri

Matthew D Hoke

Charles F Pigg

Sethu Iyer

Daniel Bodalski

Joseph W McLean

Kyle Sturgis

Oveek Mallik

Matthew Hansen

Adam D Goldberg

Liang Zhou

Prashant K Dhingra

Shailender Singh

Christopher J Leasor

Riti Singhal

Hong Ji

Song Ting Ceng

Jiangling Wang

Akshay Karnawat

James Kaczmarczyk

Rakesh Pathak

Parambir S Mudhar

Various methods, apparatuses/systems, and media for implementing a payment application module for searching billets are disclosed. A plurality of data sources include customer profile data, customer payment history data, biller information data, and biller directory data. A processor operatively coupled to the plurality of data sources via a communication network builds a customer profile service area popularity model based on the customer profile data, customer payment history data, biller information data, and biller directory data; receives search query data for searching a biller; builds a biller search machine learning model to optimize weights applied to the search query data; and ranks search results by utilizing the machine learning model in response to the search query data.

System and method for searching billers with service area popularity model and machine learning

An apparatus comprises a memory and a processor. The memory is operable to store information associated with a user account. The processor can receive a message indicating that a transaction associated with a card has occurred and receive a first input indicating that the transaction is fraudulent. The processor can receive a second input indicating that a report should be filed and present, on a display, a plurality of questions to determine whether the card has been stolen. The processor can receive a third input indicating an answer to each of the plurality of questions and present, on the display, an affidavit. The processor can receive a fourth input indicating the affidavit has been electronically signed and present, on the display, a confirmation message indicating that the report has been filed.

System and method for investigating fraudulent activity

According to one embodiment, an apparatus comprising a memory and a processor is provided. The memory is operable to store information associated with a user account. The processor can receive a message indicating that a transaction associated with a card has occurred and receive a first input indicating that the transaction is fraudulent. The processor can receive a second input indicating that a report should be filed and present, on a display, a plurality of questions to determine whether the card has been stolen. The processor can receive a third input indicating an answer to each of the plurality of questions and present, on the display, an affidavit. The processor can receive a fourth input indicating the affidavit has been electronically signed and present, on the display, a confirmation message indicating that the report has been filed.

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

Growing community of inventors

Newark, DE, United States of America

Somnath Choudhuri