Northern Trust has implemented machine learning models within its FX currency management solutions business, to provide greater oversight of thoughts of daily data points. The solution, which has been developed in partnership with Lumint, an outsourced FX execution services provider, aims to help buyside firms reduce risk in the currency management lifecycle.
The technology utilised by the Robotic Oversight System (ROSY) for the US based custodian systematically scans newly arriving, anonymised data to identify anomalies across multi-dimensional data sets. It is built on machine learning models developed by Lumint using a cloud platform that allows for highly efficient data processing.
Andy Lemon, head of currency management, Northern Trust, said, “In a data-intensive business, ROSY acts like an additional member of the team working around the clock to find and flag anomalies. The use of machine learning to detect data outliers enables us to provide increasingly robust and intuitive solutions to enhance our oversight and risk management, which can be particularly important in volatile markets.”
Northern Trust and Lumint formed a strategic partnership in 2018 to deliver currency management services with portfolio, share class and look–through hedging solutions alongside transparency and analytics tools for asset owners and asset managers.
“Northern Trust’s deployment of ROSY amplifies the scalability of its already highly automated currency hedging operation; especially for the more sophisticated products such as look-through hedging offered to its global clients,” added Alex Dunegan, CEO, Lumint.
The solution is the latest rollout of machine learning technology by Northern Trust, as the it continues to leverage new technologies across its businesses. In August last year, the custodian developed a new pricing engine within its securities lending business employing machine learning and advanced statistical technology forecast lending rates for 34 global markets.
Built on a hybrid-cloud platform, the algorithm leverages numerous strategic market data points from multiple asset classes and regions to project the demand for equities in the securities lending market.