NLP in risk management: leveraging large language models
View AgendaKey reasons to attend
- Discover practical applications of natural language processing (NLP) in risk management
- Explore controls and risk mitigation strategies for large language models (LLMs)
- Delve into current and upcoming artificial intelligence (AI) regulations
Customised solutions
Does your team require a tailored learning solution on this or any other topic?
Working with the portfolio of expert tutors and Risk.net’s editorial team, we can develop and deliver a customised learning to make the most impact for your team, from initial assessment to final review.
About the course
NLP is revolutionising the financial sector, particularly with the emergence of groundbreaking LLMs like ChatGPT. This course introduces both traditional NLP methods and the latest language models.
Participants will explore how to validate an LLM, select from various providers and libraries and learn techniques for fine-tuning these models to suit their organisation’s specific needs.
Through live demonstrations, attendees will examine successful risk management use cases, including text generation, information retrieval and extraction. Participants will also gain invaluable insights into effectively detecting, preventing and mitigating risks associated with these technologies.
This training also addresses key challenges in NLP implementation, such as ‘hallucinations’, data privacy concerns and legal risks, ensuring a safe and ethical deployment.
No prior technical knowledge is required to attend this course.
Pricing options:
- Early-bird rate: save up to $800 per person by booking in advance
- 3-for-2 rate: save over $2,000 by booking a group of three attendees
- Subscriber reward: save 30% off the standard rate if you are a Risk.net subscriber*
- Season tickets: save up to 60% - request price breakdown
*T&C apply, see registration page.
Learning objectives
- Identify key libraries and providers for LLMs
- Learn how to validate LLMs and identify inaccuracies
- Navigate bias, fairness and explainability in AI
- Examine strategies for customising and improving LLM outputs
- Understand the principles of prompt engineering
Who should attend
Relevant departments may include, but are not limited to:
- Risk management
- Risk technology
- Compliance
- Strategy
- Management
- IT and data
This course is best suited for practitioners seeking insights into the risks and opportunities of NLP technology, with a focus on large language models.
Agenda
October 22–24, 2024
Live online. Timezones: Emea/Americas
Sessions:
- Introduction to the technology
- Deep dive into large language models (LLMs)
- Tried and tested use cases
- Risk management and compliance (part one)
- Organisational implementation
- Risk management and compliance (part two)
Tutors:
- Jos Gheerardyn, Co-founder and chief executive, Yields.io
- Tonia Durfee, Executive director, UBS
- Jesús Calderón, Managing director, Maclear Data Solutions
- Federico Crecchi, Associate partner and co-head of data science, Prometeia
Tutors
Jos Gheerardyn
Founder and CEO
Yield.io
Jos Gheerardyn is at the forefront of revolutionising FinTech as the CEO and co-founder of Yield.io, an award-winning AI platform dedicated to model risk management and the first platform utilising AI for real-time model testing and validation on an enterprise scale. Passionate about algorithm monitoring, testing, and validation, Jos is an advocate for model risk governance and strategy and has 18 years of post-PhD experience in the financial services industry. Prior to his current role, he was active in quantitative finance both as a manager and an analyst. He has worked with leading international investment banks as well as with award winning start-up companies. He is the author of multiple patents applying quantitative risk management techniques on imbalance markets. Jos’ academic foundation is robust, holding a PhD in theoretical physics with a focus on superstring theory from the University of Leuven.
Jesús Calderón
Managing director
Maclear Data Solutions
Jesús Calderón advises Canadian and international clients in the financial services and energy industries on the implementation of data-driven solutions for risk management in banking, insurance, capital markets, and energy trading, as well as anti-money laundering and regulatory activities. Jesús has over twelve years of experience in risk management, internal audit, and fraud investigations, where he has specialized in the application of data science and machine learning methods to optimize risk control activities and examinations.
Federico Crecchi
Associate Partner and co-head of the data science practice
Prometeia
Federico is an associate partner and the co-head of the data science practice at Prometeia, specializing in banking analytics. He holds an M.Sc. from the University of Chicago in Physics and is a CFA charterholder. Before joining Prometeia, he worked for the Generali Group in investments and data science. Federico has successfully overseen numerous AI projects within complex institutions, spanning areas such as risk analytics, CRM enhancement, fraud analytics, and intelligent process automation.
Tonia Durfee
Executive Director, Global Compliance & Risk Group, Remediation and Integration
UBS
Dr. Durfee is an accomplished executive leader with a Ph.D. in information systems specialising in natural language processing. With over a decade of experience, she has excelled in building complex global risk management programs, optimising data infrastructure, and enhancing organisational design.
Her strategic initiatives include redesigning a graduate program curriculum, boosting enrollment by 24%, and leading projects that generated $105 million in originations for a retail bank.
Currently, as Executive Director at UBS, Dr. Durfee focuses on data governance, risk methodologies, and legal cost reporting for non-financial risk. Previously, she served as Global Head of Non-Financial Risk/Loss Data at Credit Suisse.
Pre-reading materials
The Risk.net resources below have been selected to enhance your learning experience:
- LLM integration: Special report 2024
- Dismantling the zeal and the hype: the real GenAI use cases in risk management
- How Ally found the key to GenAI at the bottom of a teacup
A Risk.net subscription will provide you access to these articles. Alternatively, register for free to read two news articles a month.