NextGeneration Counterparty Credit Risk and XVA Modeling:
AI and Quantum Computing
COURSE OBJECTIVE
Course on counterparty risk modeling in a financial institution that covers the following objectives:

Explain the recent Basel III directives on counterparty risk default capital charge, IMM and standard approaches

As well as the recent Basel III directives for the risk capital charge of Credit Value Adjustment CVA under the basic and standard approach.

Recent methodologies to calculate the XVA and the necessary adjustments in the pricing of Over The Counter OTC derivatives related to counterparty risk, financing, collateral and capital are exposed.

Models are explained to calculate the Debit Value Adjustment DVA, and other adjustments such as LVA, FVA, CollVA, KVA and XVA.

Methodologies are shown to estimate the parameters used in the CVA such as the probability of default PD, severity of loss LGD and Credit Spread using structural models and reduced form models.

Explain the modeling of current exposure and the main metrics used such as potential future exposure and expected exposure.

Present methodologies for calculating the Wrong Way Risk WWR

Evaluate some of the most used derivatives in banking.

Present counterparty risk validation techniques for CVA and Expected Exposure.

Explain CVA and XVA counterparty risk stress testing model.

ARTIFICIAL INTELLIGENCE

Show traditional and innovative artificial intelligence methodologies such as Deep Learning and machine learning to value derivatives, estimate exposures, calculate CVA and XVA.


QUANTUM ALGORITHMS and MACHINE LEARNING

Quantum mechanics is well known for speeding up statistical sampling processes over classical techniques. In quantitative finance, statistical sampling comes up in many use cases.

Quantitative algorithms for the calculation of the Credit Value Adjustment (CVA) are explained, and we expose opportunities and challenges of the quantum advantage.

We address how to obtain a quantum advantage over the Monte Carlo simulation in the pricing of derivatives.

We explain numerical analyzes to show the quantum acceleration, with respect to economic capital, on classical Monte Carlo simulations.

Quantum machine learning explained.

Use of tensor networks to improve the speed of neural networks.

WHO SHOULD ATTEND?
This program is designed for directors, managers, consultants, regulators, auditors, and counterparty credit risk analysts, as well as professionals who are implementing the Basel III regulatory agreements. It is relevant for those who work in banks, savings banks, and other companies that are exposed to credit risk. The program assumes prior knowledge of Statistics and Probability, as well as proficiency in using Excel.
You can benefit from quantum computing technologies without needing to have knowledge of quantum physics.
Price: 6 900 €
Schedules:

Europe: MonFri, CEST 1619 h

America: MonFri, CDT 1821 h

Asia: MonFri, IST 1821 h
Summer Price: 4 900 €
Level: Advanced
Duration: 30 h
Material:

Presentations PDF

Exercises in Excel, R , Python, Jupyterlab y Tensorflow
AGENDA
NextGeneration Counterparty Credit Risk and XVA Modeling:
AI and Quantum Computing
Quantum Computing and Artificial Intelligence
Module 1: 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

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

Exercise 1: Quantum operations
Module 0: Deep Learning

Definition and concept of deep learning

Why now the use of deep learning?

Neural network architectures

activation function

sigmoidal

Rectified linear unit

hypertangent

Softmax


Multilayer Perceptron

Using Tensorflow

Using Tensorboard

R deep learning

Python deep learning

Typology of Neural Networks

feedforward network

Convolutional Neural Networks CNN

Recurrent Neural Networks RNN


Use of deep learning in banking

cost function

Gradient descending optimization

Use of deep learning for the IRRBB and ALM

Deep Learning Software

Deployment software: Nvidia and Cuda

Hardware, CPU, GPU and cloud environments

Deep Learning for valuation of derivatives

Stochastic Differential Equations

Optimization models

Advantages and disadvantages of deep learning

Exercise 2: Deep learning in banking
Counterparty Credit Risk
Module 1: Counterparty Credit risk requirements in Basel III

Counterparty credit risk

Financial transactions

CCR: the risk of counterparty default

CVA: credit valuation adjustment

Basel I, II and III regulations

CVA Risk Capital Charges

Approaches Credit Value Adjustment (CVA)

The basic approach (BACVA)

The standardized approach (SACVA)


Counterparty Risk Capital (CCR)

Measurement of exposure for derivatives: SACCR

Measurement of exposure for derivatives: IMMCCR

Module 2: Counterparty Credit Risk Management

Definition and Concepts

Counterparty risk in OTC

Counterparty risk in Repos and Securities

Counterpart risk participants

Credit Exposure

PD, LGD, Parent Migration and Credit Spread

MtM and Replacement Cost

Counterparty Risk Mitigation

Measurement and adjustments

credit limits

Definition and CVA concept

Counterparty risk hedges

Counterparty risk portfolio
Main Derivatives used in Banking
Module 3: Interest Rate Futures and Options

OTC derivatives and organized markets

Futures and Swaps

Forward Rate Agreements (FRAs)

Hedging Strategies with Interest Rate Futures

Interest Rate Swaps (IRS)

Overnight Index Swaps (OIS)

Riskfree rate vs OIS

OIS zero curve

OIS vs Libor

Funding risk

CVA and DVA


Interest rate options

Bond Options

Caplets/Caps

Floorlets/Floors

swaptions

Necklace

reverse necklace


Valuation models

Pricing caps and floors using Black`s Model

Pricing with trinomial trees

Pricing of Caps and Floors using the Libor Market Model


Exercise 3: IRS Valuation in Excel

Exercise 4: Pricing of caps and floors Black`s model in Python

Exercise 5: Swaption Pricing in Excel

Exercise 6: Caplet and Swaption Libor Market Model in Python

Exercise 7: Bond Options Trinomial Tree in Excel
Module 4: Other Derivatives used in Banking

Variable Income Derivatives

Variable Income Options

Equity Swaps

Organized Market Options


Fixed Income Derivatives

Fixed income forwards


Exchange rate derivatives

Cross Currency Swap

exchange rate options


Credit Derivatives

Credit Default Swap CDS


Exercise 8: Pricing Cross Currency Swap

Exercise 9: Equity Option Pricing in Python

Exercise 10: Pricing CDS in R
Counterparty Credit Risk Exposure
Module 5: Internal model to measure counterparty risk exposure

Counterparty risk exposure modeling

MtM+Add on

Monte Carlo simulation


Potential Future Exposure (PFE)

Expected Exposure (EE)

Maximum PFE

Expected positive exposure

negative exposure

Effective expected positive exposure

Factors: maturity, payment frequencies, optionalities and default

PFE of Interest Rate Swaps, Swaptions and CDS

Netting impact on exposure

Collateralized exposure modeling

Collateral modeling

Unilateral Margin Agreement

Bilateral Margin Agreement

Collateralized Exposure Profiles

Collateralized PFE

collateralized EE

Exercise 11: MtM Simulation of IRS Securities

Exercise 12: Interest rate simulation using CIR and Vacicek model to determine IRS MtM. PFE and EE estimation

Exercise 14: Estimating EE and EPE Swaptions in Excel with VBA

Exercise 15: Estimation of collateralized and uncollateralized PE and EPE
Traditional and Quantum Deep Learning for
Derivatives Pricing and Counterparty Credit Risk Exposure
Module 6: Neural Networks for pricing derivatives

Deep Learning to value derivatives

Deep Learning to estimate exposure

Monte Carlo vs. Deep Learning

Neural Networks (Neural Networks NN)

Derivatives Valuation

Perceptron Training

Backpropagation algorithm

training procedures

Tuning NN

NN display

Advantages and disadvantages

Exercise 16: Deep Learning to assess the BlackSholes model

Exercise 17: Deep Learning for Bermuda Option valuation

Exercise 18: Deep Learning to estimate Expected Exposure
Module 7: Advanced Machine Learning for measuring volatility and exotic options

Deep Learning in volatility

Pricing and calibration

Local Volatility

implied volatility surfaces

Valuation of exotic options

derivatives pricing

Greek estimate

Exercise 19: Deep Learning Volatility
Module 8: Quantum Machine Learning

What is quantum machine learning?

Qubit and Quantum States

Quantum Automatic Machine Algorithms

quantum circuits

Support Vector Machine

Support Vector Quantum Machine

Variational quantum classifier

Training quantum machine learning models

Quantum Neural Networks

Quantum GAN

Quantum Boltzmann machines

Exercise 20: Traditional Machine Learning and Quantum Machine Learning to value a derivative
Module 9: Tensor Networks for Machine Learning

What are tensor networks?

Quantum Entanglement

Tensor networks in machine learning

Tensor networks in unsupervised models

Tensor networks in SVM

Tensor networks in NN

NN tensioning

Application of tensor networks in credit scoring models

Exercise 21: Derivatives valuation model using Neural Networks versus neural network tensorization
Quantum Computing Finance
Module 10: Quantum Computational Finance

Derivatives pricing

Monte Carlo to value derivatives

Quantum algorithms for derivatives

European option pricing using quantum algorithms

Basket Options Pricing Using Quantum Algorithms

Quantum generative antagonistic networks

Exercise 22: Pricing of derivatives using Monte Carlo versus quantum algorithms

Exercise 23: Basket Options Pricing using classical deep learning and quantum deep learning
Credit Value Adjustment
Module 11: Structural Models of Default Probability of Default

Merton's model

Physical Probability of Default

BlackScholesMerton model

Black–Cox model

Vasicek–Kealhofer model

CDS Pricing

Curves in liquidity and nonliquidity conditions

CDS Implied EDF

CDS Spreads

Fair Value Spread

CDS Spread in Sovereigns

Exercise 24: CDS Spread and PD Exercise
Module 12: Reduced Form Models Probability of Default

Credit Spread Modeling

Credit Spread Smoothing

Adjusting credit spread with cubic splines


Reduced form models

JarrowTurnbull Model

Duffie and Singleton Model

Neutral default probabilities

Conversion of default currents into discrete PDs

Adjustment of reduced form models to historical databases

Construction of default probability curves

Validation with Falkenstein and Boral Test


Jump to default

Zero coupon bonds

Voucher with coupons

convertible bonds

CDS


SpreadRisk

Default probability for companies without market information

Exercise 25: Construction of probability of default and hazard rate curves
Module 14: Advanced Loss Given Default (LGD)

Definition: LGD, RR and CRR

collateral treatment

Linear approach to estimating LGD

Approach with Options BlackSholes to estimate LGD

LGD Implied in CDS Spread

Calibration and optimization of Implicit LGD using binomial trees

Expert LGD models using decision trees

Exercise 26: LGD estimation using the linear approach and BlackSholes

Exercise 27: Implicit LGD estimation through binomial trees and optimization
Module 15: CVA in Basel III

Minimum capital requirements for CVA risk

The basic approach (BACVA)

Reduced version of the BACVA method (without recognition of hedges)

Full version of the BACVA method (with recognition of hedges)

admissible coverages

KIntegro

KAdmissible

KCovered


The standardized approach (SACVA)

CVA calculations for regulatory purposes

admissible coverages

Model Risk Multiplier

capital requirements for delta and vega risks

Categories, risk factors, sensitivities, risk weights, and correlations


Exercise 28: Calculation of BACVA and SACVA
Module 16: Credit Value Adjustment (CVA) Modeling

Definition and CVA concept

Formula and parameters

Factors Affecting CVA

Risk management by CVA

Collateralized Counterparties

Hedge on market factors

spread hedge


CVA seen as Spread

Adverse Correlation Risk

CVA mitigation mechanisms

Marginal CVA and Incremental CVA

CVA modeling with reduced form model

CVA in IRS

CVA in IRSs portfolio

riskneutral probability

Simulation


Exercise 29: Estimating CVA, EE, PFE

Exercise 30: CVA estimating in IRS portfolios using Monte Carlo simulation
XVA
Module 20: What is XVA?

XVA concept

CVA, DVA, LVA, FVA, CollVA, KVA

Profitability in derivatives

Regulatory perspective

XVA Trading

New XVA Trader Features

CSA basis Price

Collateral and OIS as discount rate

Pricing and Negative Multicurve in the XVA framework
Módulo 21: Debt Value Adjustment (DVA)

Definition of Debt Value Adjustment (DVA)

IFRS accounting standard

Bilateral CVA

DVA Properties

Risk Adjusted Value

DVA Monetization

DVA Hedge or Transfer to Treasury

LVA Concept

Exercise 35: Bilateral CVA Estimation
Módulo 22: Funding Value Adjustment (FVA) Deep Learning para XVA

Concept of Value Adjustments for financing costs

Overnight Indexed Swaps (OIS) vs. bank interest rates

FVA discussion

FVA formula: Negative and Positive

CVA, DVA and FVA Interaction

Cost of Funding

Net Stable Funding Ratio Impact

Liquidity Premium

Risk Adjusted Value

Alternative FVA estimate

Collateral Cost Adjustment Formula CollCA and MVA

HVA Hedging Cost Adjustment Formula

FVA Estimate

KVA Capital Cost Estimate

XVA calculation

XVA Risk Management

Deep Learning for XVA

Exercise 36: XVA Calculation in Python

Exercise 37: Estimating CVA, DVA, FVA, CollVA, HVA, KVA, LVA and XVA in Excel

Exercise 38: Deep Learning for XVA

Exercise 39: Quantum computing for XVA
MODEL VALIDATION
Module 23: Validation of Counterparty Credit Risk

RFE validation

Risk Factor Evolution (RFE) Models

stochastic equations

historical calibration

Analysis of Empirical Distributions vs. Estimated Distributions

statistical analysis

AndersonDarling

Kolmogorov Smirnov

Cramer von Mises

traffic light analysis


Problems in the validation of counterparty risk models

Autocorrelation effect

Sound practices for backtesting CCR models from Basel

PFE Backtesting

binomial distribution


CVA Backtesting

traffic light analysis

Berkowitz backtesting strategy


Exercise 40: Backtesting the PFE using AD, KS and CV test
STRESS TESTING
Module 24: Stress testing of Counterparty Credit Risk

Stress testing expected exposure

PFE stress testing

Stress testing on the counterparty's PD

Stress testing using VAR and MVAR

Macroeconomic variables


CVA and DVA stress testing

Liquidity shock on FVA

Stress Testing in KVA and CET1

General Wrong Way Risk

XVA stress testing

Quantum model for stress testing

Exercise 41: CVA and EE stress testing

Exercise 42: PD stress testing using VAR and MVAR