Can robots learn to manage risk?

Will machine learning transform risk management or give birth to a new breed of model risk? Probably both

From the shiny corridors of BlackRock’s Palo Alto laboratory, to the cramped shared workspaces of scientifically minded hedge fund start-ups, to the hallways of quantitative investing stalwarts such as Renaissance Technologies and Two Sigma, artificial intelligence (AI) is being adopted as the new temple of asset management. Even discretionary managers are starting to bring in data scientists and machine learning experts.

Most attempts to apply AI so far have been in stock price forecasting. But risk managers are asking how the technology can be harnessed in their domain also. One area of exploration is the use of machine learning to replace traditional approaches to risk modelling.

Conventional risk models often treat markets as webs of essentially linear relationships. Each factor that contributes to risk gets a weighting – and those weightings don’t change. That’s a problem, as it tends to miss tail risks, according to Gareth Shepherd, managing partner at G Squared Capital, a London-based discretionary firm using machine learning to better understand idiosyncratic risk.

“The traditional approach equity research analysts take of using linear regression and bell curves to model idiosyncratic risk is a fairly antiquated tool.
It’s like putting a horizontal ruler on a spherical Earth and trying to measure it. It’s just a weird
thing to do,” he says.

Dario Villani, chief executive of machine learning hedge fund Duality Group, says current risk models fly in the face of the fact that assets are driven by elusive, shifting relationships, rather than fixed laws of risk and return. Villani is one of a group of quants who see machine learning as transformative, potentially unlocking the secrets of this non-linear behaviour.

In a non-linear machine learning model, the weighting would change over time, depending on a multitude of factors. For example, non-linear prepayment models for agency mortgage-backed securities built by MSCI depend on 30–100 variables that interact with each other differently depending on whether the loan is in or out of the money.

But do the new techniques harbour risks of their own? Yes, they do.

Models in general can go wrong by picking up on false patterns in data, or simply through being too hard to understand. Both faults are amplified many-fold by AI because the datasets are so much bigger and the algorithms themselves so much more complicated. BlackRock shelved some liquidity risk models built using neutral networks because it couldn’t understand their inner workings. These risks will require careful handling.

Data analysis

In other areas, though, intelligent machines will face fewer obstacles. The use of machine learning to automate data analysis is one way CROs might get closer to real-time risk management.

Darrel Yawitch, chief risk officer at Man Group, one of the world’s largest hedge funds, which is using AI in client portfolios for pattern recognition and anomaly detection, has said the last financial crisis might have been avoided had machine learning been available to analyse subprime mortgage pools data.

In this area, the robot march looks inevitable. As Jody Kochansky, head of BlackRock’s Aladdin risk management platform, which handles about $15 trillion in assets, or about 7% of the world’s financial assets, told Risk.net last year: “The world at large is automating the daylights out of everything, and financial services is no different.”