Posts

QuantMinds e-magazine, June 2020

New research, new breakthroughs, and new opportunities

With the results of my latest work with Brian Huge on differential machine learning, along with the latest from Marcos Lopez de Prado, Alexander Antonov, Svetlana Borovkova, and Fabio Mercurio, who have shared their latest insights into machine learning (ML), neural networks, covid-19 and Libor.

Differential machine learning combines ML with automatic differentiation (AAD) to produce accurate pricing and risk approximations for arbitrary derivatives transactions or trading books, quickly, online, with convergence guarantees.

No alternative text description for this image
QuantMinds e-magazine, June 2020

interactive magazine here

Differential Machine Learning

Risk management with AAD and ML: an unreasonably effective combination

Working paper: on ssrn
GitHub: github.com/differential-machine-learning
TensorFlow notebook: on Google Colab

Differential machine learning (ML) is an extension of supervised learning, where ML models are trained on examples of not only inputs and labels but also differentials of labels to inputs, applicable in all situations where high quality first order derivatives wrt training inputs are available.

In the context of financial Derivatives and risk management, pathwise differentials are efficiently computed with automatic adjoint differentiation (AAD). Differential machine learning gives us unreasonably effective pricing and risk approximation. We can produce fast pricing analytics in models too complex for closed form solutions, extract the risk factors of complex transactions and trading books, and effectively compute risk management metrics like reports across a large number of scenarios, backtesting and simulation of hedge strategies, or regulations like XVA, CCR, FRTB or SIMM-MVA.

The article focuses on differential deep learning (DL), arguably the strongest application. Standard DL trains neural networks (NN) on punctual examples, whereas differential DL teaches them the shape of the target function, hence the performance. We included numerical examples, both idealized and real world.

In the online appendices, we apply differential learning to other ML models, like classic regression or principal component analysis (PCA), with equally remarkable results.

We posted a TensorFlow implementation on Google Colab, including examples from the paper and a discussion of practical implementation.

Open In Colab
basket option price approximation from simulated data
with standard and differential deep learning

Article with code, Wilmott Mar20

The third and final part of my paper  “Computation graphs for AAD and Machine Learning part III: Application to Derivatives Sensitivities” was just published in Wilmott, the third and final in a series of three articles with code dedicated to AAD and Computational Finance in general. It covers computation graphs, backpropagation, AAD and implementation in finance, taking inspiration in the recent achievements of the Superfly Analytics group of Danske Bank.

The first parts were published in Wilmott November 2019 issue and  Wilmott January 2020 issue.

A. Savine, “Computation graphs for aad and machine learning part iii: application to derivatives sensitivities” Wilmott, vol. 2020, iss. 106, p. 24-39, 2020.