Large Language Models (LLMs) in Finance Certificate - Self Paced (Coming soon to The Quants Hub)
Duration:
📅 Self-Paced: 21+ Lecture Hours
Format:
💻 Online
Evaluation:
✔ Final Project + Certificate
📆 Time Commitment:
Recorded lectures accessible any time. Take the LLM at your own pace.
🕛 Self-paced Online:
Students will have the opportunity to apply what they learn in hands-on projects throughout the course.
📊 Certificate:
“Students are awarded the prestigious LLM Certificate from The Artificial Intelligence Finance Institute’s (AIFI)”
💳 Cost: £895.00
Designed for students who need further flexibility, this self-study option contains all you need to prepare for 
the LLM final real-world project.
The course consists of 9 Modules:
- Introduction to LLMs
- Applications and Limitations of LLMs
- Advanced Techniques with LLMs
- Quantization and Sharding for LLMs
- Fine-Tuning and RAG Introduction
- Deep Dive into RAG and Evaluation
- LLMs Agents, AI Safety and Finance Examples
- Practical Applications and Real World Project
- Real World Project
About the programme
The integration of Large Language Models (LLMs) into finance is revolutionizing the industry, offering new ways to process information, analyze data, and interact with customers. This course by the Artificial Intelligence Finance Institute delves into the essentials of LLMs, their practical applications in finance, and hands-on implementation techniques. From understanding the architecture of LLMs to deploying them for financial analysis and customer service, participants will learn to harness the power of AI to innovate and improve efficiency in the financial sector. Whether you’re a finance professional, a developer, or a student, this course provides the knowledge and skills needed to navigate the future of finance with AI.
The Large Language Models (LLMs) in Finance Certificate will guide participants through the essentials of LLMs, including their architecture, operation, and the latest advancements in the field. It will delve into the practical aspects of deploying these models for financial tasks, such as fine-tuning for domain-specific applications, implementing retrieval-augmented generation for enhanced information processing, and evaluating model performance. Through a series of hands-on examples and projects, learners will gain the skills necessary to apply LLMs effectively within the finance sector, addressing real-world challenges and unlocking new opportunities.
Final Project
The LLM concludes with a practical final project that gives you the opportunity to implement the knowledge and skills you have acquired during the course of the programme. Self Study Pack students get an option three times per year to join the live cohort (when ready) to discuss the Practical Applications and Final Real World Project with the faculty.
The purpose of this project is to enable students to practically apply the techniques and concepts learned throughout the course to a real-world financial use case. This hands-on experience will help solidify your understanding and demonstrate your ability to utilize LLM in solving complex financial problems. You are required to select a practical use case within the finance sector where you can apply LLM techniques. The project should encompass one or combined techniques learned during the course (Prompt engineering, Fine-tuning, RAG, Agents....).
Modules:
Module 1: Introduction to LLMs (2 hours)
Introduction (30 minutes)
LLMs Foundations (1 hour and 30 minutes)
- What is an LLM? (Overview, Transformer architecture, Encoder + Decoder Architecture, etc.)
Module 2: Applications and Limitations of LLMs (2 hours)
Continuation of LLM Foundations (30 minutes)
- Examples of LLMs, Tokenization and Embedding
Limitations of LLMs (30 minutes)
- Knowledge Cutoff, Domain Specific Challenges, Solutions
Running LLM Locally (1 hour)
Module 3: Advanced Techniques with LLMs (2 hours)
Prompt Engineering (1 hour and 30 minutes)
- Exploration of techniques such as zero-shot learning, few-shot learning, etc.
Fine-Tuning Introduction (30 minutes)
- Introduction to Fine-Tuning, PEFT
Module 4: Quantization and Sharding for LLMs (2 hours)
Introduction to Quantization (1 hour)
- What is Quantization?
- Benefits of Quantization in LLMs
- Practical Examples of Quantization in Finance
Introduction to Sharding (1 hour)
- What is Sharding?
- How Sharding Optimizes LLM Performance
- Implementing Sharding in Financial LLM Applications
Module 5: Fine-Tuning and RAG Introduction (3 hours)
Continuation of Fine-Tuning (1 hour)
- RLHF, LoRa, QLoRa, Practical Examples
- DPO,KTO
RAG (Retrieval-Augmented Generation) (2 hour)
- RAG Explanation, Why to Use RAG?
Module 6: Deep Dive into RAG and Evaluation (2 hours)
Continuation of RAG (1 hour)
- RAG Components, Last RAG Advancement Techniques, Practical Examples
Evaluation (1 hour)
- Introduction to LLM Evaluation, Evaluation Metrics and Methods, Using Trulens
Module 7: LLMs Agents, AI Safety and Finance Examples (3 hours)
LLM Agents (1 hour)
- Introduction to LLM Agents in Finance
- Use Cases and Implementation Strategies
- Building and Deploying LLM Agents for Financial Services
AI Safety (1 hour)
- Understanding AI Safety
- Tools and Strategies for AI Safety
- AI Safety in Finance
LLMs in Finance: Practical Examples (1 hour)
- Financial Report Parsing, Sentiment Analysis
Module 8: Practical Applications and Real-World Project (2 hours)
Continuation of LLMs in Finance: Practical Examples (1 hour)
- Extracting Insights: Trends and Analysis, Trading
Real World Project (1 hour)
- Option 1: Parsing Financial Reports
- Option 2: FullStack Application
Module 9: Real World Project (2 hours)
Continuation of Real-World Project (2 hours)
- Completion of chosen project