Derivatives Pricing, Artificial Intelligence and Quantum Algorithms
COURSE OBJECTIVE
Intensive and advanced course on the valuation of derivative products of variable income, fixed income, exchange rate and credit using traditional models, artificial intelligence and quantum computing.
The course shows strategies and hedging with options, advanced pricing models for interest rate options, implicit, local and stochastic volatility models and the Jump Diffusion Model.
For the valuation of interest rate options, there is a module that deals with the construction of the Yield Curve because it is extremely important for the valuation of interest rate derivative models. The Libor transition and the creation of the SOFR yield curve have been updated, which will impact the pricing of derivatives and XVA.
Innovatively, the use of powerful machine learning tools is exposed, particularly neural networks and deep learning, for the valuation of derivatives, calibration of stochastic differential equations, estimation of implicit volatility and creation of the yield curve.
The valuation of first and second generation exotic options is explained, 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.
Price: 8.900 €
Schedules:

Europe: MonFri, CEST 1620 h

America: MonFri, CDT 1821 h

Asia: MonFri, IST 1821 h
Level: Advanced
Duration: 40 h
Material:

Presentations PDF

Exercises in: Excel, R, Python and Jupyterlab
AGENDA
Derivatives Pricing, Artificial Intelligence and Quantum Algorithms
Modular Agenda
Artificial Intelligence in Finance
Module 2: AI in Finance (optional)

AI artificial intelligence in finance

Definition of Machine Learning

Machine Learning Methodology

Data Storage

Abstraction

Generalization

Assessment


Supervised Learning

Unsupervised Learning

Reinforcement Learning

deep learning

Typology of Machine Learning algorithms

Steps to Implement an Algorithm

Information collection

Exploratory Analysis

Model Training

Model Evaluation

Model improvements


Machine Learning in Finance

Applications in the valuation of options, projections, asset management and trading
Module 1: Deep Learning (optional)

Definition and concept of deep learning

Why now the use of deep learning?

Neural network architectures

Activation function

Sigmoidal

Rectified linear unit

Hypertangent

Softmax


Feedforward network

Multilayer Perceptron

Using Tensorflow

Using Tensorboard

R deep learning

Python deep learning

Convolutional Neural Networks

Use of deep learning in image classification

cost function

Gradient descending optimization

Using deep learning for credit scoring

How many hidden layers?

How many neurons, 100, 1000?

How many times and size of the batch size?

What is the best activation function?


Deep Learning Software: Caffe, H20, Keras, Microsoft, Matlab, etc.

Deployment software: Nvidia and Cuda

Hardware, CPU, GPU and cloud environments

Advantages and disadvantages of deep learning

Feedforward neural network

Multilayer Perceptron

Convolutional Neural Networks

Use of deep learning in image classification

recurrent neural networks

Temporal series

Long Short Term Memory

Exercise 1: Deep Learning feedforward perceptron neural network
Module 0: Quantum computing and algorithms (Optional)

Future of quantum computing in banking

Is it necessary to know quantum mechanics?

QIS Hardware and Apps

Quantum operations

Qubit representation

Complex numbers

Measurement

Overlap

Matrix multiplication

Qubit operations

Multiple Quantum Circuits

Entanglement

Deutsch Algorithm

Quantum Fourier transform and search algorithms

Hybrid quantumclassical algorithms

Quantum annealing, simulation and optimization of algorithms

Quantum machine learning algorithms

Quantum limitation

Quantum computers

Exercise 2: Quantum computing operations