Generative AI for Asset Management Workshop
Oct 2-3, 2023
2 day, in person workshop
Toronto
20 Bay Street
Hosted By
Dr. Chan & Dr. Hunter
Questions?
Email us: info@predictnow.ai
This is a 2-day in-person hands-on workshop to explore how asset managers can use a large language model (LLM) such as OpenAI’s GPT-3.5 models to compute sentiment ratings on public companies. The workshop hosts (Dr. Ernest Chan, Founder and CEO of Predictnow.ai, and Dr. Roger Hunter, Chief Technology Officer at QTS Capital Management) will provide an overview of the capabilities and limitations of LLMs, and then demonstrate how we can easily use GPT-3.5 to compute sentiment scores of companies that result in similar outcomes as expensive sentiment products. We will then break into small groups to explore and experiment with variations and improvements on the basic code, as well as brainstorm other use cases of LLM for asset management.
The workshop will be held on October 2-3, 2023 at 20 Bay Street in Toronto, where deep learning, the foundational technology behind GPT, was born.
Use the code EARLYBIRD50 to save 50% ($1000 USD) on your ticket purchase. Applicable to first 10 registrants only.
Intended Audiences
Asset Managers
Venture Investors
Entrepreneurs
Product Developers
Regulators
Finance & AI Researchers
While the intended audience for this event includes, asset managers, venture investors, entrepreneurs, product developers, regulators, finance and AI researchers. If you fall into another category but feel like you would be a good fit for this workshop, send us an email at info@predictnow.ai and we can help clarify any questions you have.
Workshop Hosts
Dr. Ernest Chan
Founder and CEO of Predictnow.ai
Dr. Roger Hunter
CTO of QTS Capital Management
Keynote Speaker
Dr. Lisa Huang
Head of AI Investment Management, Fidelity Investments.
Workshop Outline
01
Large Language Models (LLMs) and Generative Pre-trained Transformers (GPT)
- Introduction to LLMs: ChatGPT and other large language models
- Typical Applications of LLMs
- How LLMs work
- Using ChatGPT on the web and GPT-3.5 through the API
02
Building Applications
- Overview of Prompt Engineering
- Building applications such as text generation, summarization, etc.
- Few-shot learning with GPT-3.5
- Introduction to embeddings
- Overview of the OpenAI embeddings API and its usage
03
Risks Associated with LLMs
- Understanding main risks with LLMs, such as, hallucinations, bias, consent and security
- Methods for reducing the risks of Hallucinations, such as, retrieval augmentation, prompt engineering, and self-reflection
- Methods to detect and address hallucinations, including reinforcement learning from human feedback (RLHF) and model-based approaches
04
Using GPT for sentiment analysis
- Why we chose the OpenAI GPT-3.5 family among the many available LLMs
- Evaluating GPT-3.5’s native performance
- Improving performance with embeddings
- Worked example: computing sentiment ratings on public companies using embeddings
- Test data: financial sentences with sentiment labels, built from two datasets (FiQA, Financial PhraseBank) combined into one easy-to-use CSV file. It is freely available from https://www.kaggle.com/datasets/sbhatti/financial-sentiment-analysis.
05
Deploying GPT and Other Language Models in Production
- Best Practices for Deploying GPT in Production
- Overview of alternative generative models such as Cohere, LLaMA, Alpaca, etc.
Venue Information
Use the code EARLYBIRD50 to save 50% ($1000 USD) on your ticket purchase. Applicable to first 10 registrants only.
