Northern Trust Develops Google-Inspired Pricing Engine

Northern Trust has developed a pricing engine that uses machine learning and statistical analysis techniques to forecast loan rates in the securities lending markets.

“For this project, our data scientists applied a time series algorithm to the problem of securities lending. Specifically, we have used some techniques inspired by Google technologies,” Chris Price, a specialist enterprise architect at Northern Trust, says.

Time series analysis harnesses a set of machine learning and statistical tools for predicting future conditions based on past data. Northern Trust’s algorithm uses market data from various asset classes and regions to project the demand for equities in the securities lending market. The firm’s global securities lending traders can combine these projections with their own market intelligence to automatically broadcast lending rates for 34 markets to borrowers.

“We are able to forecast rates that we observe in the market for the benefit of traders [and] consolidate large volumes of data into a view of where we think rates are headed over the short term. This is a process that traders would do themselves today, but we are able to use the algorithm to do it more rapidly,” Price says.

Dane Fannin, head of global securities lending at Northern Trust, says that while securities lending is largely automated, the pricing component for a subset of these securities is very labor intensive “because a trader needs to look at a particular line item of a security and understand where they should price that relative to demand and supply.”

Traders want to automate this process because it has to be done on tens of thousands of assets, he says. “So what we have done is pull out an algorithm that replaces the process a trader would undertake anyway, but in a more sophisticated fashion using additional data points to complement that process.”

Fannin says there is a lot more scope to apply artificial intelligence and machine learning in the securities lending market.

“We are focused on continuing to develop this out across broader asset classes [and] components of the trading decision-making cycle. We are going to stay close to our client base in that regard. We are aware that many market participants—from user to borrower, including our clients—are exploring and using new technologies, so it feels critical that we as a firm continue to look at these and remain competitive.”