Machine Learning for Risk Calculations: A Practitioner's View (The Wiley Finance Series)

As the computational demand of risk calculations in financial institutions has exploded, many of these same organizations have sought an alternative to running enormous farms of CPUs and GPUs in order to price complex financial instruments, as well as detect and measure hidden or unexpected risks. Algorithmic solutions, grounded on Deep Learning and Chebyshev Tensors, represent a central family of these types of alternatives.

In Machine Learning for Risk Calculations: A Practitioners View, Ignacio Ruiz and Mariano Zeron deliver practical strategies to reduce costs while simultaneously increasing risk calculation capabilities. The book includes numerical tests and examples demonstrating how these solutions can be applied, as well as a companion website from which you can download a software suite used throughout the book.

Youll be able to follow along and experiment with your own calculations as you read about improving risk management without putting unrealistic computational burdens on your systems.

The book reviews the fundamental techniques involved in Deep Learning, Chebyshev Tensors and the algorithmic tools that, in combination with these techniques, help to solve the problem of computational overload. It also discusses how these solutions can be applied to practical problems in the real world, like XVA and counterparty credit risk, IMM capital, PFE, Market Risk VaR and FRTB, dynamic initial margin simulation, pricing function calibration, volatility surface parametrization, portfolio optimization, exotic pricer sensitivities and more.

Perfect for quants, IT professionals and quantitative risk managers in financial institutions, Machine Learning for Risk Calculations is an indispensable guide to the use of algorithmic solutions for the problem of massive computational burdens imposed by risk calculations in financial institutions.

MACHINE LEARNING FOR RISK CALCULATIONS

Reduce computational overload and improve risk calculations at your financial institution with deep learning and tensoring techniques

Few techniques offer as much potential for reducing the computational demand of risk calculations as algorithmic solutions based on Deep Learning and Chebyshev Tensors. These practical strategies significantly reduce costs while increasing risk calculation capabilities.

Machine Learning for Risk Calculations: A Practitioners View offers readers an in-depth review of many of these algorithmic solutions and demonstrates how to use them in real-world situations.

Youll find applicable and concrete solutions to practical problems, including XVA and counterparty credit risk, IMM capital, PFE, Market Risk VaR and FRTB, dynamic initial margin simulation, pricing function calibration, volatility surface parametrization, portfolio optimization, exotic pricer sensitivities and more.

The book comments on existing software libraries for Deep Learning and Chebyshev Tensors. In particular, a companion website (mocaxintelligence.org) offers a software suite for Chebyshev Tensors that you can download and, together with your favourite Deep Learning library, this can be used to follow along with the book and experiment with your own calculations as you review fundamental and advanced topics.

Ideal for quants, IT professionals, and financial risk managers, Machine Learning for Risk Calculations is an indispensable, practitioner-oriented guide to state-of-the-art risk calculation.