The Bank of New York Mellon Corporation

Bryan Chan

Brian Blank

Madhusudan Rana

Song He

Pavithran Rajendran

Methods and system are described for optimizing data processing in cloud-based, machine learning environments. For example, through the use of a machine learning model utilizing a self organizing map and/or the use of specific processing nodes in a computer system to perform specific tasks the methods and system may more efficiently distribute tasks through a cloud computing environment and increase overall processing speeds despite increasing amounts of data. The methods and system described herein are particularly related to collateral allocation computer systems that automate the management of numerous collateral assets. For example, as the amount of collateral assets and the complexity of given transactions grow, typical allocation systems face frequent processing delays related to collateral allocations (e.g., allocations of collateral associated with Tri-Party Repos).

System and method for optimizing data processing in cloud-based, machine learning environments through the use of self organizing map

A computer-implemented system and method for managing collateral allocations associated with Tri-Party repurchasing agreements and a collateral allocation system includes one or more processors and memory/database configured to store user-definable rulesets and collateral characteristics relating to the Tri-Party repurchasing agreements. A collateral allocation module recalls collateral from the Tri-Party repurchasing agreements to a common Dealer Box, and reallocates the collateral to the Tri-Party repurchasing agreements utilizing a self organizing map, so as to minimize margins to reduce over-collateralization and/or undercollateralization. Other considerations, such as basket identifiers and cost of carry considerations may be weighed in the reallocation as well.

Growing community of inventors

East Meadow, NY, United States of America

Bryan Chan