Bank of America Corporation

Kolt Bell

Craig Douglas Widmann

Scott Anderson Sims

Dharmender Kumar Satija

Amijo Bearley

Andrew DongHo Kim

Michael Joseph Carroll

Elliot Piatetsky

Sai Kishan Alapati

Stephen M Schneeweis

Alvino Sarran

Alex Stapleton

Michael E Toth

John Tuders

David Barnhardt

Daniel Van Vliet

David Kerman

Michael Ayers-Morris

Robert D Jones

Robert J Dominguez

Eren Kursun

Hitesh Shah

Youshika C Scott

Brian H Corr

Roberto Jose Dominguez

Jeff Zusi

Nicole Ryan

Brandon Weeks

Paulette Price

Shawn Parris Bench

Susan M Sullivan

Aspects of the disclosure relate to deploying and utilizing a dynamic record identification and analysis computer system with event monitoring components. A computing device may receive account reconnaissance data identifying a first plurality of user accounts that have experienced at least one event associated with account security concern characteristics. The computing platform may analyze event history data associated with the first plurality of user accounts to identify one or more common interactions associated with a subset of the first plurality of user accounts. The computing platform may identify a point of compromise among the subset of the first plurality of user accounts. Subsequently, the computing platform may search enterprise user account records to identify a second plurality of user accounts that have at least one event associated with the point of compromise. The computing platform may add the second plurality of user accounts to an alert table.

Dynamic record identification and analysis computer system with event monitoring components

Systems, computer program products, and methods are described herein for cross platform user event record aggregation system. The present invention is configured to receive one or more exposure events from one or more detection systems; determine that a combination of at least a portion of the one or more exposure events indicates an intrusion in at least one of the one or more detection systems, thereby requiring elevated review of each exposure event; initiate the elevated review based on at least the indication of the intrusion; determine whether the intrusion is benign or harmful; and re-train the machine learning algorithm based on at least determining whether the intrusion is benign or harmful, thereby adjusting the score for future incidents of each exposure event in the combination of at least a portion of the one or more exposure events.

Cross platform user event record aggregation system

Systems, computer program products, and methods are described herein for elevated authentication model using cross-channel data. The present invention is configured to receive one or more exposure events from a detection system, wherein at least one of the one or more exposure events indicates that a user has failed an authentication requirement in at least one communication channel associated with the detection system; store the one or more exposure events in a centralized repository; determine one or more other communication channels across the one or more detection systems available for access to the user; and increase an authentication requirement of the user in the one or more other communication channels, wherein increasing the authentication requirement further comprises increasing an authentication level required to enable the user to access at least one of the one or more functions associated with at least one of the one or more applications.

Cross channel authentication elevation via logic repository

Systems, computer program products, and methods are described herein for the creation of an exposure identification and distribution system for across silo channel integration. In this way, the system allows team integration of data across rails and silos for exposure identification. As such, the system generates a centralized repository for data and a communication linkage across the various systems used for identifying exposure and manipulated for linkage via a specific taxonomy overlay. Furthermore the system also includes logic that, when identification of a potential exposure indicate occurs, the system may communicate via distribution over the rails for integration and sharing for cross entity exposure identification.

System for across rail silo system integration and logic repository

The invention describes a system and method employing machine learning and artificial intelligence engines to monitor data streams in real-time across multiple channels in order to detect anomalies and generate prioritized alerts. In particular, the invention may continuously collect data across multiple channels. The obtained data may be compared with reference data to continuously update a confidence level associated with the user, channel, entity, or other identifying factor. The invention may detect any inconsistencies in the data collected over time and generate an alert to the user in question and potentially to other downstream users or entities. In this way, the invention not only provides a way to detect anomalies in a cross-channel fashion, but also creates a mechanism for feedback wherein the system may incorporate user feedback to resolve alerts and detected anomalies.

Cross-channel detection system with real-time dynamic notification processing

An illustrative method for identifying information associated with a ring of individuals performing improper financial activities may include combining a list of user identifiers with one or more attributes tables corresponding to the financial transactions. A computer device may analyze a first list of identifiers in relation to an attribute table, where the identifiers may be associated with one or more suspected improper financial activities and the attribute table may include attributes of one or more financial transactions performed over a specified duration. The computer device may then link the first list of identifiers with one or more attributes included in the attribute table to determine a second list of identifiers and the process may be repeated until a stopping condition has been reached. After the stopping condition has been met, the computer device may communicate a report to a user.

Improper financial activity detection tool

Aspects of the disclosure relate to a system to monitor devices for unauthorized access of an external account. A computing platform may receive, via a communication interface, and from a first user device, metadata comprising first user device identification information and accessed account information. The computing platform may determine, based on the first user device identification information, whether the first user device is one of a plurality of internal user devices. The computing platform may identify, based on the accessed account information, an action indicating the first user device is accessing an account. The computing platform may determine, based on the action and the accessed account information, whether the action is authorized. The computing platform may receive information indicating unauthorized use of the account by the first user device. The computing platform may transmit the information indicating unauthorized use of the account by the first user device.

Internal footprint repository

Systems and computer-readable media are disclosed for utilizing one or more databases to detect a point of compromise ('POC'). A POC detection computing platform may receive data associated with a potential point of compromise from a first computing system. The POC detection computing platform may extract data associated with the potential point of compromise from one or more central servers and/or databases. The extracted data may then be analyzed to determine if a point of compromise has been detected. The POC detection computing platform may transmit the results of the analysis to a second computing system.

System for utilizing one or more databases to identify a point of compromise

Aspects of the disclosure relate to deploying and utilizing a dynamic record identification and analysis computer system with event monitoring components. In some embodiments, a computing platform may receive, from a contact feed generation computer system, one or more contact feeds comprising contact data identifying one or more contacts associated with one or more user accounts. The computing platform may analyze the one or more contact feeds to identify a first subset of user accounts of the one or more user accounts having one or more attributes associated with one or more predetermined account security concern characteristics. Subsequently, the computing platform may add the first subset of user accounts of the one or more user accounts to an alert table maintained by the computing platform, and may send, to an analyst computer system, alert table listing information identifying contents of the alert table maintained by the computing platform.

Methods and apparatus according to the invention are directed towards providing means for identifying a selection of entity associates that may contain a perpetrator of claimed fraud against an entity account. Means are also provided for scoring the associates within the selection as to relative likelihood of being the perpetrator. Identification means and scoring means may include analyses of the number and nature of connections associates may have with the frauded account, with other entity accounts, with past claims of fraud, and with other associates.

Associate risk analysis

Growing community of inventors

Charlotte, NC, United States of America

Kolt Bell