World Business StrategiesServing the Global Financial Community since 2000

Day 1: Thursday 16th May

08.30 – 09.00

Registration and Welcome Coffee

09.00 – 10.30: Recent Developments in Mathematical Climate Finance (Extended Talk followed by Q&A)

  • Carbon equivalence principle for asset pricing
  • Minimization of carbon costs
  • Carbon-linked financial products
  • CO2eVA: how to adjust derivatives valuation for carbon price risk
  • Probabilistic transition-risk pricing methods for financial instruments

Andrea Macrina:

Professor of Mathematics, University College London (UCL)

Chris Cormack:

Co-founder and Managing Director, Quant Foundry

10.30 – 11.00: Morning Break and Networking Opportunities

11.00 – 11.45: Embedding Climate Risk & The Brave New Normal for Quants

Rutang Thanawalla:

Visiting Fellow, London Institute of Banking & Finance & Strategic Adviser, Climate Tech

11.45 – 12.30: Corporate Sustainability Affecting Average Returns

The impact of Environmental Social and Governance (ESG) factors on the performance of listed stocks is still controversial in the literature. We aim to identify groups of companies according to their ESG temporal dynamics to evaluate whether their fluctuations impact the market risk factors. We assess a potential relationship between financial and non-financial risks within the Fama and French framework (Fama and French, 2015) according to the ESG score and its components. We discriminate companies which increase their ESG compliance using a hierarchical time-series clustering approach and computing the similarity between two-time series by Euclidean distance and Dynamic Time Warping (DTW). The latter is useful when the time series have different shifts and speeds. We compare four hierarchical methods with different linkage criteria (average, complete, Ward.D, Ward.D2). The optimal number of clusters is selected based on four cluster validity indices (Silhouette, Calinski-Harabasz, Clustering Order Preservation, and Dunn). The data utilized in this paper refer to the S&P500 and come from the Refinitiv database (Refinitiv, 2023). The cluster validity indices indicate two clusters as the best choice. However, while the Euclidian distance with the average method is the best combination for the ESG score and its components E and S, the DTW distance with the ward.D method is the best for the G score. Overall, we find different effects on the market risk, companies who are classified as “committed” toward sustainability show a different sensitivity to the market excess return factor respect to the less committed companies. The other risk factors seem to have little impact on the committed or uncommitted companies.

Rita Laura D’Ecclesia:

Professor of Quantitative Finance. Sapienza University of Rome, Italy

12.30 – 13.30: Lunch

13.30 – 14.15: Navigating the Environmental, Social, and Governance (ESG) landscape: Constructing a robust and reliable scoring engine

Nicole Königstein:

Chief Data Scientist, Head of AI & Quant Research, Wyden Capital AG

14.15 – 15.00: Transition Risk for Mortgage Portfolios: From Energy Labels Forecasting to Stress Testing

Svetlana Borovkova:

Climate Risk Quant Research, Bloomberg

15.00 – 15.30: Afternoon Break and Networking Opportunities

15.30 – 16.15: Foundation NLP Models for ESG data extraction

  • Learning not to “make stuff up”
  • SFT (Supervised Fine Tuning)
  • RLHF (Reinforcement Learning with Human Feedback)

Robert Dargavel Smith:

Director of Machine Learning Engineering , Clarity AI

16.15 – 17.00: Integrating Large Language Models for Enhanced ESG and Climate Risk Analysis in Finance

In this session, we’re diving into how Large Language Models (LLMs) can be used in ESG and climate risk analysis for finance. We’ll break down how these AI tools help us sift through huge amounts of data to spot risk patterns and insights that might not be obvious at first glance. We’ll see firsthand the value of LLMs in understanding and managing the risks tied to ESG. Will look into how to leverage these technologies for a more informed decision-making approach in finance.

David Pacheco Aznar:

Founding Partner & Chief of AI Research and Development, Raven Risk AI

17.00 – 17.45: Panel: The Impact of Large Language Models and Generative AI on ESG Sustainability Goals

  • How sustainable is AI and LLM? What can be done to make it more sustainable and help companies, like Quant funds, meet their ESG goals?
  • AI and in particular LLM are becoming more ingrained in everyday society – is there sufficient Data Center capacity in Europe to accommodate this and Quant fund growth in the years to come
  • Can adopting a hybrid IT strategy, for example by using a combination of On Premise and Cloud (public and private), reduce costs and CO2 emissions?
  • Greenwashing is becoming a relevant issue for listed companies, How companies can apply safeguards and mitigants to address potential greenwashing risks?
  • AI and LLM allow to capture non linearities in relationships between ESG features and structural features of the firms. How can this help companies to comply with the regulator requirements?
  • Can AI and LLM help companies to integrate sustainability risks in the decision making process and organizational requirements
  • What do you see as the greatest risks of using generative AI in the context of ESG / Sustainability?

Svetlana Borovkova:

Climate Risk Quant Research, Bloomberg

Robert Dargavel Smith:

Director of Machine Learning Engineering , Clarity AI

Andrea Macrina:

Professor of Mathematics, University College London (UCL)

David Pacheco Aznar:

Founding Partner & Chief of AI Research and Development, Raven Risk AI

Nicole Königstein:

Chief Data Scientist, Head of AI & Quant Research, Wyden Capital AG

  • Discount Structure
  • Special Offer
    When two colleagues attend the 3rd goes free!

  • 70% Academic Discount
    (FULL-TIME Students Only)

Download Event PDF

Please enter your details to download this PDF

Error

Event Email Reminder

Error