LLMs in Finance

Repository for the course "Large Language Models in Finance" - Barcelona School of Economics (BSE) Summer School 2025.

📚 Course Overview

This 5-day intensive course explores the application of Large Language Models (LLMs) in financial contexts. From foundational concepts to advanced applications, the course provides both theoretical knowledge and hands-on experience with state-of-the-art language models for financial analysis, sentiment prediction, risk assessment, and more.

Learning Objectives

By the end of this course, you will be able to:

• Understand the architecture and capabilities of modern LLMs
• Apply LLMs to various financial use cases using appropriate prompt engineering techniques
• Evaluate and mitigate limitations and biases in LLM applications for finance
• Implement advanced techniques including fine-tuning and structured generation
• Design and develop practical LLM-powered applications for financial analysis

🗓️ Course Structure

📌 Day 0: Course Introduction

• Instructor introduction
• Course overview and learning outcomes
• Technical requirements

📌 Day 1: Introduction to Large Language Models

• Introduction to LLMs, architectures, capabilities, and limitations
• Environment setup and configuration
• HuggingFace and API integrations
• Financial sentiment analysis examples

📌 Day 2: LLM Training & Prompting

• Training methodology and techniques
• Zero-shot and few-shot learning approaches
• Prompt engineering best practices
• Chain-of-thought reasoning for complex financial problems

📌 Day 3: Financial Applications I

• Valuation and DCF modeling with LLMs
• Financial forecasting techniques
• Comparables selection using natural language understanding
• Building financial analysis tools

📌 Day 4: Financial Applications II

• Credit risk assessment
• Mathematical modeling with LLMs
• Advanced transformer applications in finance
• Model evaluation and performance metrics

📌 Day 5: Advanced Techniques & Future Directions

• Return forecasting with LLMs
• AI in asset management
• Reinforcement learning applications
• Ethical considerations and future trends

📘 Preliminaries

For those new to Python or needing a refresher, we provide preparatory materials covering:

• Python fundamentals with NumPy and PyTorch
• Introduction to vectors and tensors for neural networks
• Basic finance concepts for the course

📂 Repository Contents

This repository contains all course materials including:

• Lecture slides for each day
• Practical notebooks with hands-on exercises
• Example code and demonstrations
• Financial datasets for exercises

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

📧 Contact

Juan F. Imbet - Course Instructor Barcelona School of Economics, 2025