In this workshop, you will learn practical techniques for customizing LLMs for quant finance using prompt engineering, retrieval augmentation, and fine-tuning.
Prior knowledge of LLMs or Python programming is not required. Open-source examples that work without an expensive GPU will be provided for those interested in running and modifying the code.
Models: GPT-3.5, GPT-4, Llama 2, Code Llama
Session One: Prompting and Retrieval Augmentation
- Prompting – natural language programming of LLMs
- Principles of prompt engineering
- Prompt types
- Retrieval augmentation – using information outside model training
- Embedding – asking questions over documents
- Chains – multi-step workflows
- Memory
- Overcoming limitations
- Context window
- Large documents
- Hallucinations
- Reproducibility
- Performance Optimization
- CPU and GPU performance profiles
- Quantization
- Hands-on examples with Python
- Comprehension of trade confirmations
Q&A
Session Two: Fine-Tuning
- Unsupervised fine-tuning
- Expanding the model dataset and vocabulary
- Self-supervised fine-tuning
- Reducing prompt length
- Supervised fine-tuning
- Generated datasets
- Curated datasets
- Performance Optimization
- LORA and QLORA
- Hands-on examples with Python
- Generation of draft model release notes
Q&A
The workshop day on Wednesday 27th September will be complimentary to all delegates.
The workshop will include two 1:45 hour sessions (13:00 – 14:45 and 15:00 – 16:45) with 15 min coffee break after the first session and 15 min Q&A after the second session.

Alexander Sokol:
Executive Chairman and Head of Quant Research, CompatibL
Alexander Sokol: Executive Chairman and Head of Quant Research, CompatibL
Alexander Sokol is the founder, Executive Chairman, and Head of Quant Research at CompatibL, a trading and risk technology company. He is also the co-founder of Numerix, where he served as CTO from 1996 to 2003, and the co-founder of Duality Group, where he served as CTO from 2017 to 2020.
Alexander won the Quant of the Year Award in 2018 together with Leif Andersen and Michael Pykhtin, for their joint work revealing the true scale of the settlement gap risk that remains even in the presence of initial margin. Alexander’s other notable research contributions include systemic wrong-way risk (with Michael Pykhtin, Risk Magazine), joint measure models, and the local price of risk (with John Hull and Alan White, Risk Magazine), and mean reversion skew (Risk Books, 2014).
Alexander earned his BA from the Moscow Institute of Physics and Technology at the age of 18, and a PhD from the L. D. Landau Institute for Theoretical Physics at the age of 22. He was the winner of the USSR Academy of Sciences Medal for Best Student Research of the Year in 1988.
Wednesday 27th September:
Informal Meetup Drinks – Ghecko from 8pm
Address: Plaça del Negret, 2, 46001 València, Valencia, Spain
If you fancy a stroll into the Old town (Ciutat Vella) on your first night in Valencia, come and join for an informal meetup before the main conference starts on the Thursday morning. Bar Ghecko is a 20 minute wander from the hotel.
ESG and climate risk are the most talked about topics in investment and risk management at the moment. In this workshop, we will address both issues from a quantitative perspective, addressing the necessary data issues, emerging evidence and models, but will also discuss what regulators currently have to say about both issues.
Session 1: Climate risk modelling for financial institutions
- Finding your way in current regulatory climate risk environment
- Physical vs transitional risk
- Climate risk for various asset classes: such as equity, corporate credit and mortgages
- Climate scenario analysis: NGFS and other scenarios
- Current practices in climate risk modelling and emerging modelling approaches
- Data sources and data issues for various types of climate risk and asset classes
- Climate stress testing: from stressed asset valuations to stressed PDs
- Several industry case studies: climate risk in equity and corporate credit portfolios
Session 2: Measuring and managing ESG in asset management and banks
- Regulatory aspects of incorporating ESG considerations in investment and banking
- Measuring ESG: ESG metrics and ratings, data types, sources and providers
- Defining and measuring a financial institution’s own sustainability criteria
- Managing ESG: portfolio construction and portfolio management strategies
- Relationships between sustainability, financial performance and risk
- Impact investing and green bonds: what are the quantitative issues?
The workshop day on Wednesday 27th September will be complimentary to all delegates.
The workshop will include two 1:45 hour sessions (13:00 – 14:45 and 15:00 – 16:45) with 15 min coffee break after the first session and 15 min Q&A after the second session.

Svetlana Borovkova:
Head of Quantitative Modelling, Probability & Partners. Associate Prof, Vrije Universiteit Amsterdam
Svetlana Borovkova: Head of Quantitative Modelling, Probability & Partners and Associate Professor, Vrije Universiteit Amsterdam
Dr Svetlana Borovkova is the partner and Head of Quant Modelling of risk management consulting firm Probability and Partners and an Associate Professor of Quantitative Finance and Risk Management at the Vrije Universiteit Amsterdam. She is the author of over 60 academic and professional publications and a frequent speaker at conferences such as RiskMinds and QuantMinds. Her work encompasses a wide range of topics, ranging from derivatives pricing and risk modelling to sentiment analysis for quant investing and machine learning in quant finance. Find her work at SSRN and her columns on various finance topics in Financial Investigator.
Wednesday 27th September:
Informal Meetup Drinks – Ghecko from 8pm
Address: Plaça del Negret, 2, 46001 València, Valencia, Spain
If you fancy a stroll into the Old town (Ciutat Vella) on your first night in Valencia, come and join for an informal meetup before the main conference starts on the Thursday morning. Bar Ghecko is a 20 minute wander from the hotel.