Machine Learning for Market Risk

Door Svetlana Borovkova, Head of Quantitative Modeling

In two recent columns, I discussed the current state of Machine Learning (ML) applications in finance (February 15, 2022) and the use of ML in credit (November 23, 2021). Recently, a new class of machine learning algorithms – the so-called autoencoders – was proposed for market risk applications by Prof. John Hull, well-known for his famous book about derivatives, and his co-author Alexander Sokol.

I heard their talks on this at the latest Risk Minds conference in December and immediately got so excited by this ingenuous application of machine learning, that we are already implementing and extending it in within our quant team at Probability & Partners.

One of the main problems in assessing the market risk of (large) portfolios is the multidimensionality of the task. Portfolios typically comprise tens if not hundreds of assets – stocks, commodities, indices, ETFs and other instruments. Treating each of them as an individual risk factor is not feasible. A similar problem arises when modelling interest rate curves or implied volatility surfaces (volatilities for different option strikes and maturities) – these problems are also multivariate in nature.

To ease the modelling task, one would like to find a smaller set of (often unobservable) latent risk factors, which, when taken together, explain most of the risk of a large portfolio. In interest rate curves, these latent factors are the level, the slope and the curvature of the curve. These three factors can explain 99% of all interest rate moves. But how can we find such factors for more complicated situations, such as large diversified investment portfolios or implied volatility surfaces? This is where autoencoders can help.

Neural networks

An autoencoder is a type of a neural network: the most popular class of machine learning models. A neural network consists of nodes, also called neurons, which are arranged in the input layer, hidden layers and the output layer, these layers being sequentially connected. The goal of a neural network is to predict an outcome on the basis of a set of features, just as in traditional regression.

For example, the outcome might be the price of a security in the next trading period, the price and the delta of an option, or the credit rating of a loan holder. The nodes in the input layer receive the information about features (for instance previously observed prices, trading book features, option parameters or characteristics of a loan holder), process it in a certain way and transfer it to the first hidden layer, where the process is repeated, and so on, until the output layer is reached.

The information processing in the nodes is done in such a way that the predicted output maximally matches the actual observed output – the network ‘learns’ these processing rules on the basis of a multitude of examples presented to it. This process is called training. Then the trained network is tested on the examples it has never seen before. The architecture of a typical neural network is so flexible and its generalization power is so great, that it can learn very complex relationships between the input and the output.

Autoencoders

While the goal of a typical neural network is to predict a response on the basis of features, an autoencoder is designed to perform a seemingly useless task: to recover the input information. But first, this information has to go through an intermediate layer with very few nodes – as few as three or four – which is called the bottleneck.

Essentially, an autoencoder is a ‘compressor’, or encoder of information, which is decoded once it passes through the bottleneck. Autoencoder ‘decides’ on the most efficient way of encoding the input, without any guidance from the modeler.

In a way, it is similar to the well-known statistical technique of Principal Component Analysis (PCA). But while PCA’s latent factors are linear functions of the original features, an autoencoder can encode them in a much more flexible way, using any imaginable nonlinear combinations of them.

And this is where the magic happens: imagine that the input features are the returns of many assets in a large portfolio, a set of interest rates for different maturities or implied volatilities for a multitude of options’ maturities and strikes. Then the compressed information coming out of the bottleneck will be exactly these few ‘hidden’ risk factors, that drive almost the entire portfolio risk, interest rate curve’s or implied volatility surface’s evolution.

In this way, we handle the risk resulting from many actual risk factors by modelling just a few latent factors and then ‘decoding’ them back to the full risk factor universe.

Applications

While the main application of such autoencoders is market risk modelling, they can also be used for recovering realistic interest rate curves from ‘corrupted’ or incomplete quotes, or for generating implied volatilities for illiquid  or unobserved strikes and maturities. But for now, there are more questions than answers and efficient algorithms for these applications still need to be developed and tested – something our quants at Probability & Partners are enthusiastically working on.

Get in touch with us if you want to know how Machine Learning can be applied to problems in your organization, and how you can make your risk management and modelling more efficient with ML techniques.

More news

Amba Zeggen
trade export controls webinar
Hospital Cybersecurity
Pim Poppe
Pim Poppe
Yusi Wang
Pim Poppe
Advanced data analytics professional working with servers at Probability & Partners data center.
Rens Borsje
Pim Poppe
Professional business team of three smiling in formal attire.
Businessman looking at a world map on a wall with a date overlay June 26.
Rens Borsje
Professional business team in formal attire smiling at the camera.
Pim Poppe
Webinar: - AI Language Learning Models
Lush green forest with river and fog, February 27.
Yusi Wang
EU regulations notebook with European flag and pen on dark surface.
Quantifying CSRBB Shocks using PCA
Digital human face with neural network connections and data streams.
Legal gavel, glass sphere, and open book for CSRD webinar on Nov 28.
Edward Roozenburg
DORA Webinar (14-11)
Regulations and compliance document with torn paper effect.
Compass on financial data and spreadsheets for financial analysis.
European Union flags outside a modern government building in Brussels.
Kevin Rojer
Webinar: Modelvalidatie bij pensioenfondsen en de transitie
Manos Ieronymakis
Webinar Sleutelfunctiehouder Risicobeheer Wtp
Amba Zeggen
Webinar: DORA
Yusi Wang
Van risico-inventarisatie naar risicobeoordeling: Waar kan de eerste lijn_SFH zich op focussen
Svetlana Borovkova
Pim Poppe
Ronald Sijsenaar
Edward Roozenburg
EBA Roadmap on EU Banking Package
Wat is de rol van de sleutelfunctiehouder risicobeheer in de transitie naar het nieuwe pensioenstelsel
Edward Roozenburg
Edward Roozenburg
Edward Roozenburg
Pim Poppe
Renze Munnik
Pim Poppe
Renze Munnik
Gerd-Jan van Wiggen
Amba Zeggen
Amba Zeggen & Rens Borsje
Renze Munnik
Machine Learning
Koen van Ederen
Renze Munnik
Amba Zeggen
Gerd-Jan van Wiggen
Het pensioenakkoord: wat komt er op de bestuurstafel?
Pim Poppe
A note on prepayment modelling for residential mortgages
A note on prepayment modelling for residential mortgages
Financial Investigator
Reinforced Learning for Hedging_ Transfer Learning at Work
Model Risk Management_ Fundamental Concepts
A note on prepayment modelling for residential mortgages
Pim Poppe
A note on prepayment modelling for residential mortgages
Fundamental Review of the Trading Book_ An Overview of Key Components
Amba Zeggen
Pim Poppe
Amba Zeggen
Sustainable factor investing during the covid-19 pandemic
Amba Zeggen
Het pensioenakkoord: Wat komt er op de bestuurstafel
A note on prepayment modelling for residential mortgages
A note on prepayment modelling for residential mortgages
Emerging macroeconomic trends in the post-COVID-19 world_ An investor’s perspective
Pim Poppe
IT maturity and the DNB IT framework
Cybersecurity during and after the corona crisis
Corona risk management_ board-related, operational, financial
Inflation risk and pensions: Should we worry?
IORP II: De gevolgen
A note on prepayment modelling for residential mortgages