Deep learning techniques are increasingly used in finance. This poses real challenges to regulators. In this 3 half-day conference, academic researchers, practitioners and regulators will discuss how to implement in practice state-of-the-art deep learning techniques for asset and risk management, and how to regulate their use.This event is co-organized by the FaIR program at Institut Louis Bachelier (ILB-FaIR), Electricité de France (EDF), Autorité de Contrôle Prudentiel et de Résolution (ACPR) and the Alan Turing Institute. 

This event will be held online.

REGISTRATION

Full program

Day 1 – AI-based Asset & Risk Management
Monday 27/09 (9:00-12:30 AM CET) 

Summary 
AI computation of trading and hedging strategies has opened up new opportunities, including the possibility to solve high-dimensional problems, the management of constraints (liquidity, transaction costs, proxy hedging), and a more flexible choice of the criterion to be optimized. In this session, we will present the latest improvements to these methods and their operational use.

 

9:00 – 9:05 Welcome AddressMarie Brière (Director of the FaIR program, Institut Louis Bachelier)

9:05 – 9:50 Arnulf Jentzen (University of Münster & The Chinese University of Hong Kong)
Title: Convergence analysis for gradient descent optimization methods in the training of ReLU neural networks

9:50 – 10:35  Josef Teichmann (ETH Zurich)
Title: Deep Asset Liability Management

10:35 – 11:00  Break

11:00 – 11:45 Joseph MIKAEL (EDF – Senior Research Engineer)
Title: A Quick Overview of EDF’s AI Research and Applications in Finance Related Activities

11:45 – 12:30 Round Table: AI-based Asset & Risk Management
Moderator: Huyen Pham (University Paris 7 – Paris Diderot)
Panelists: Thomas Deschatre (EDF – Financial Engineer), Arnulf Jentzen (University of Münster & The Chinese University of Hong Kong), Josef Teichmann (ETH Zurich)

12:30 End of Day 1

 

Day 2 – Generative Methods for Simulations and Risk Management
Tuesday 28/09 (9:00 – 12:30 AM CET) 

Summary 

Generative methods (GAN, VAE etc.) applied to time series simulations allow to flexibly update the model without having to spend time designing a new stochastic model. However, the direct application of Generative Adversarian Networks (GANs) to time series is not straightforward. We present recent advances in time series generation and discuss the questions they raise.

 

9:00 – 9:05 Welcome AddressJoseph Mikael (EDF – Senior Research Engineer)

9:05 – 9:50 Lukasz Szpruch (University of Edinburgh & Alan Turing Institute)
Title: Neural SDEs and their Offsprings in Risk Management

9:50 – 10:35 Blanka Horvath (King’s College & Technical University of Munich & Alan Turing Institute)
Title: Kernel Methods in Generative Modelling

10:35 – 11:00 Break

11:00 – 11:45 Edmond Lezmi (Amundi, Head of Multi-Asset Quantitative Research)
Title: Trading Strategy Backtesting with Boltzmann Machines and Generative Adversarial Networks

11:45 – 12:30 Round Table: Generative Methods for Risks Simulations
Moderator: Joseph Mikael (EDF – Senior Research Engineer)
Panelists: Romuald Elie (Université Gustave Eiffel), Blanka Horvath (King’s College & Technical University of Munich & Alan Turing Institute), Edmond Lezmi (Amundi, Head of Multi-Asset Quantitative Research), Lukasz Szpruch (University of Edinburgh & Alan Turing Institute)

12:30 End of Day 2

 

Day 3 – Confidence and Regulation of AI-based Algorithms
Wednesday 29/09 (9-12:30 AM CET) 

Summary 
AI brings a lot of improvements to the financial industry: faster and more flexible, AI algorithms tend to deliver better forecasts, simulations or internal controls. However, there is a lack of confidence when it comes to industrial implementation of AI: insufficient unit tests, lack of theoretical guarantees, data sensitivity. We will discuss how to build explainability and confidence in AI algorithms, from both the regulators and industry point of view.

 

9:00 – 9:05 Welcome AddressOlivier Fliche (ACPR – Head of Fintech/Innovation department)

9:05 – 9:50 Jean-Michel Loubes (Université Toulouse Paul Sabatier)
Title: What solutions can be Provided Using Mathematical Tools?

9:50 – 10:35 Stéphane Crépey (Université de Paris)
Title: Darwinian Model Risk and Reverse Stress Testing

10:35 – 11:00 Break

11:00 – 11:45 Olivier Fliche (ACPR – Head of Fintech/Innovation department)
Title: Gouvernance of AI Algorithms in the Financial Sector

11:45 – 12:30 Round Table: Confidence and Regulation of AI-based Algorithms
Moderator: Marie Brière (Amundi – Head of Investor Research Center)
Panelists: Stéphane Crépey (Université de Paris), Olivier Fliche (ACPR – Head of Fintech/Innovation department), Jean-Michel Loubes (Université Toulouse Paul Sabatier), Joseph Mikael (EDF – Senior Research Engineer)

12:30 End of Day 3 – End of Conference

 

REGISTRATION

 

Organizing committee : 

    • Louis Bertucci (FaIR – ILB)
    • Marie Brière (FaIR – ILB)
    • Olivier Fliche (ACPR)
    • Joseph Mikael (EDF)
    • Lukasz Szpruch (Alan Turing Institute)

 

 

 

 

Organisers
Finance and Insurance Reloaded (FaIR)
Electricité de France (EDF)
Autorité de Contrôle Prudentiel et de Résolution (ACPR)
The Alan Turing Institute

Location

online