Derivatives Pricing, Artificial Intelligence and Quantum Algorithms
Advanced course on valuation of derivative products using traditional models, AI, and quantum computing for variable income, fixed income, exchange rate, and credit.
The course covers various topics related to options trading, including hedging strategies and advanced pricing models for interest rate options. It also covers implicit, local and stochastic volatility models, as well as the Jump Diffusion Model.
To properly value interest rate options, a module is dedicated to the construction of the Yield Curve, which is crucial for the valuation of interest rate derivative models. The course also covers the recent Libor transition and the creation of the SOFR yield curve, which will impact the pricing of derivatives and XVA.
Moreover, the course introduces the application of machine learning tools such as neural networks and deep learning to value derivatives, calibrate stochastic differential equations, estimate implicit volatility and create the yield curve.
The course explains how to value exotic options of the first and second generation using machine learning models.
Numerical methods are exposed, such as partial differential equations, PDEs, trinomial trees and traditional Monte Carlo simulation, in addition to increasing calculation speed, pricing of options is explained through Fourier transformations and improvements in Monte Carlo Simulation. To significantly speed up the estimation of the Greeks, the Adjoint of Automatic Differentiation algorithm has been included.
The course has a significant number of exercises in Julia, Python and R as well as case studies that enhance learning. The advantages and disadvantages of each language for the valuation of derivatives are addressed. We have introduced a new language, called Julia, which is powerful, simple and very fast. All exercises in the JupyterLab environment.
Monte Carlo simulation is the most widely used technique to value derivatives. However, banks are turning to machine learning in an attempt to give their pricing models a boost. The technique consists of training deep neural networks to approximate the results to Monte Carlo models without having to run millions of simulations. The neural network approximates the price of your portfolio when you run a gigantic and complicated XVA.
XVA valuation adjustment methodologies are exposed, among other models: estimation of credit exposure, Credit Value Adjustment CVA, debit value adjustment DVA, Funding Value Adjustment, CoLVA, MVA and KVA, exposing traditional methodologies and deep learning models.
Pricing is a computationally demanding task that is traditionally solved using Monte Carlo simulation techniques. However, Quantum Accelerated Monte Carlo (QAMC) quantum computing techniques promise quadratic acceleration over Monte Carlo (MC) simulation, this quantum advantage of increasing computational speed would bring substantial benefits, particularly for the huge volume of derivative products what is on the market.
The quantum advantage of QAMC over MC simulation and the advantage of quantum machine learning over the traditional one will be exposed.
Didactic course, clearly presented, with the experience and quality of Fermac Risk, seeking to make the participant's learning the most important thing. The course is practical to apply what is learned immediately at work.
WHO SHOULD ATTEND?
People who work in the following departments: Investment Management, Treasury, Credit Risk Analysis, Portfolio Modeling, Model Validation, Quantitative Research, Structuring, Pricing, Market Risk, methodologies, financial management, financial controllers and Portfolios managers. From banks, brokerage firms, corporations, insurance, stockbrokers, brokerage firms and stockbrokers.
The course does not address abstract mathematics or complex theory. Nevertheless, the mathematical models are seriously explained. The student will know not only the theory but also practical exercises. It is advisable to master some programming language.