Generative AI for Finance

Course Overview

This seven hour workshop will cover everything you need to know to understand the current trends in generative AI, how these models work and how to train them, and how you can leverage them for the finance industry as your competitive edge. Our focus will be on gaining familiarity with high level concepts, understanding how to use these technologies, and maximizing business impact. All hands-on programming will be done in Python using Google Colaboratory. Attendees should be comfortable with the basics of programming, but need no background in data science or AI. You leave with hands-on experience and fully functioning code to apply generative AI to a number of critical business cases.

Prerequisites

Attendees should be comfortable with the basics of programming, but need no background in data science or AI.

Certificate

Certificates are awarded at the end of the program at the satisfactory completion of the course. Students are evaluated on a pass/fail basis for their performance on the required homework and final project (where applicable). Students who attend a minimum of 85% of the class are eligible for the certificate of completion.

Syllabus

Unit 1: Working with APIs

• REST API basics
• Working with OpenAI’s API offerings and python client
• Working with Huggingface’s python client
• Working with Weaviate, a vector database

Unit 2: Build your own semantic search engine

• Preparing data
• Choosing and using a vectorize
• Defining a schema and importing data
• Querying and controlling output

Unit 3: Connecting semantic search to LLMs

• Retrieval augmented generation
• Open domain question answering
• Summarization and main idea extraction
• Sentiment analysis

Unit 4: Roll your own Bloomberg GPT

• Question answering
• Summarization
• Sentiment analysis

Unit 5: Generating synthetic data

• What is synthetic data and when should you use it?
• Synthetic generation of private data
• Stress testing on synthetic macroeconomic scenarios
• Synthetic data generation of macroeconomic scenarios with GPT-3
• Developed by NVIDIA – Yi Dong, Emanuel Scoullos

Unit 6: Using language models in your workflow

• Chain of thought reasoning to explain output
• Self debate to explore latent knowledge
• Using LLMs to write SQL queries
• Using LLMs to aid in data analysis