top of page

Stress Testing for Credit Risk Quantum AI






Intensive and modern credit risk stress testing course using advanced econometric models, artificial intelligence and quantum computing. The stress tests will test the resilience of banks against an adverse macroeconomic scenario due to assumptions of stagflation, recession of the economy, severe shocks in vulnerable sectors affected by the COVID-19 pandemic, energy crisis triggered by the invasion Russian Ukraine and geopolitical tensions in China.

The new directives on Basel regarding Stress Testing are explained. Stress testing models are exposed during the COVID-19 pandemic as well as new recovery scenarios after the pandemic. Stress testing regulations and exercises are explained: EU-Wide Stress Testing for the year 2023 and Comprehensive Capital Analysis and Review in the United States.

The course explains the use of artificial intelligence in stress tests with the aim of improving the accuracy of the projections, the interpretability of the results, the ability to capture the adaptive behavior of companies and households in the face of structural ruptures in the environment. economy and the halting of supply chains as has occurred during Covid-19.

The accuracy of projections in stress testing can be difficult to achieve due to limited knowledge about the macroeconomic impacts on the profitability, liquidity and soundness of financial companies. Therefore, the course explains to the participant the use of artificial intelligence as a viable option to improve the accuracy of the projections due to the models' ability to capture non-linear effects between the scenario variables and the risk factors that drive the solvency of a financial entity.


The advantages of artificial intelligence models over stress testing models based on traditional econometric models are reviewed.


Dynamic Stochastic General Equilibrium (DSGE) models are a sub-class of applied general equilibrium economic models, widely used for creating Stress Testing scenarios. However, when neural networks are applied in the DSGE, they offer the following advantages: ability to solve high-dimensional problems and high approximation power outside the steady state. But deep learning has limitations and Monte Carlo simulation is essential, so it is possible to use quantum Monte Carlo simulation to improve speed over traditional simulation.

These are the particular objectives of the course.


  • Expose the impact of COVID-19 on banking, inflation, economic recession, energy crises and geopolitical tensions in financial institutions through stress testing practices and scenario analysis.

  • Measure and manage credit risk stress testing in corporate and retail portfolios using econometric models and improvements through artificial intelligence and quantum computing.

  • Explain the impact of COVID-19, recession and inflation on the credit quality of assets and particularly on the estimation of the Expected Credit Losses ECL of IFRS 9.

  • It discusses how to incorporate climate change financial risks into existing financial risk management practice, how to use scenario analysis to inform strategy setting, and risk assessment and identification.

  • Present methodologies to create climate change scenarios and their conversion into macroeconomic scenarios to develop stress testing models.

  • Explain the principles of Basel Stress Testing. The impact and cost-benefit of the directives in financial institutions is analyzed.

  • Teach cutting-edge methodologies to calibrate the PD IRB in retail, corporate, bank and sovereign portfolios.

  • Offer a very important number of PD, LGD and EAD Stress Testing methodologies.

  • Present LGD stress test models for Low Default Portfolio and mortgage portfolios.

  • Address validation methodologies of Stress Testing models.

  • Show how to build scenario analysis of stress testing econometric models.

  • Explain DSGE models and improvements using artificial intelligence and quantum computing.

  • Model the Lifetime PD, LGD and EAD of Expected Credit Losses using state-of-the-art methodologies including machine learning models.

  • Explain methodologies to model the charge-off, net charge-off, recoveries, balances for the estimation of the ECL Loss Rate Approach of IFRS 9.

  • Show ECL IFRS 9 Stress Testing methodologies, SICR and transition matrices

  • Analyze the stress tests in EU-Wide Stress Testing 2023 and the Comprehensive Capital Analysis and Review 2023.

  • Review the effectiveness of Stress Testing in a financial institution with practical examples on limits, capital ratios, KPIs and triggers.

  • A global exercise of Stress Testing, capital management, financial projections of the balance sheet and income statement is exposed, measuring, not only, the impact of stressful scenarios on capital and RWAs, but also the impact on profitability metrics such as KRIs, RAPMs, RARWAs, KPIs, etc.




This program is aimed at directors, managers, consultants, regulators, auditors and credit risk analysts, as well as those professionals who are implementing Stress Testing models. Professionals who work in banks, savings banks and all those companies that are exposed to credit risk. It is important to have knowledge of Statistics and Probability as well as Excel.




computadora-cuantica-cerca-imagen-ai-generativa-tecnologia-futurista (1).jpg

Price: 8.900 €





  • Europe: Mon-Fri, CEST 16-20 h


  • America: Mon-Fri, CDT 18-21 h

  • Asia: Mon-Fri, IST 18-21 h






Level: Advanced


Duration: 40 h




  • Presentations PDF

  • Exercises in Excel, R, Python and Jupyterlab 

  • The recorded video of the 40-hour course is delivered.


 Stress Testing for Credit Risk
Quantum AI



Anchor 10


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

  • Measurement

  • Overlap

  • matrix multiplication

  • Qubit operations

  • Multiple Quantum Circuits

  • Entanglement

  • Deutsch Algorithm

  • Quantum Fourier transform and search algorithms

  • Hybrid quantum-classical algorithms

  • Quantum annealing, simulation and optimization of algorithms

  • Quantum machine learning algorithms

  • Exercise 1: Quantum operations

bottom of page