Northern Trust unveils machine learning tool for price forecasting
13 August 2019 Chicago
Image: Shutterstock
Northern Trust is set to apply a machine learning-powered pricing ‘engine’ to its securities lending business for the first time in a bid to improve forecasting of rates for its lendable securities and increase revenue.
The asset manager has developed an algorithm built on a hybrid-cloud system to leverage numerous strategic market data points from multiple asset classes and regions to project the demand for lendable equities in the market.
A Northern Trust spokesperson explained: "The engine’s ability to generate an accurate forecast rests upon both the advanced techniques utilised within the model as well as the extensive breadth and depth of data used to identify trends across a set of factors."
The datasets are both internal and external and relate to securities lending specific data in addition to market data on the specific security across the cash and derivatives market, the spokesperson added.
According to Northern Trust, its global traders are able to use these projections, together with their own market intelligence, to automatically broadcast lending rates for 34 global markets to Northern Trust’s extensive network of borrowers.
Northern Trust predicts borrowers will benefit from it providing more transparency and updated pricing on its lendable portfolio, while lenders will benefit from “enhanced revenue”. The asset manager was unable to offer a specific timeframe for when lenders will see the improved returns or a scale for what the greater revenue might be.
As of June, Northern Trust had approximately $1.2 trillion in lendable assets for more than 450 clients worldwide, including custody and third-party lending.
Dane Fannin, global head of securities lending at Northern Trust, said: “The potential benefits from machine learning techniques extend beyond this initial application, and we will continue exploring and developing solutions that drive value for our clients.”
He added: "Within securities lending specifically, there are opportunities to continue investing in technologies that will help derive these outcomes beyond the pricing engine we have currently developed."
The asset manager has developed an algorithm built on a hybrid-cloud system to leverage numerous strategic market data points from multiple asset classes and regions to project the demand for lendable equities in the market.
A Northern Trust spokesperson explained: "The engine’s ability to generate an accurate forecast rests upon both the advanced techniques utilised within the model as well as the extensive breadth and depth of data used to identify trends across a set of factors."
The datasets are both internal and external and relate to securities lending specific data in addition to market data on the specific security across the cash and derivatives market, the spokesperson added.
According to Northern Trust, its global traders are able to use these projections, together with their own market intelligence, to automatically broadcast lending rates for 34 global markets to Northern Trust’s extensive network of borrowers.
Northern Trust predicts borrowers will benefit from it providing more transparency and updated pricing on its lendable portfolio, while lenders will benefit from “enhanced revenue”. The asset manager was unable to offer a specific timeframe for when lenders will see the improved returns or a scale for what the greater revenue might be.
As of June, Northern Trust had approximately $1.2 trillion in lendable assets for more than 450 clients worldwide, including custody and third-party lending.
Dane Fannin, global head of securities lending at Northern Trust, said: “The potential benefits from machine learning techniques extend beyond this initial application, and we will continue exploring and developing solutions that drive value for our clients.”
He added: "Within securities lending specifically, there are opportunities to continue investing in technologies that will help derive these outcomes beyond the pricing engine we have currently developed."
NO FEE, NO RISK
100% ON RETURNS If you invest in only one securities finance news source this year, make sure it is your free subscription to Securities Finance Times
100% ON RETURNS If you invest in only one securities finance news source this year, make sure it is your free subscription to Securities Finance Times
