Master's Degree in Economics and Finance

Master's Degree in Specialized Economic Analysis

Master's Degree in Data Science

Admissions

Career Services

Alumni Community

Economics Program

Financial Economics Program

PhD Economics Track Program

Go to Master's degrees

Close

Data Science

Large Language Models in Finance

Applying Large Language Models to financial analysis: Hands-on training and ethical insights.

17.5h (5 days)

€1,470

Face-to-face

English

Next edition: July 5-9, 2027

Early Bird deadline: April 15, 2027

Learn more

Data Science

Large Language Models in Finance

Complete your details and we'll keep you informed about the next edition

First Name*

Last Name*

Email Address*

Message

I give my consent to be contacted by BSE with information about related academic offers in the future.

Who is this Course for?

Data Science in Finance

Large Language Models in Finance

Course overview

This course is designed to immerse participants in the use of Large Language Models (LLMs) in Finance, with a strong emphasis on practical applications. Participants will learn how LLMs work, what they can and cannot do, and how to turn them into reliable tools for financial analysis. Each day combines a lecture with a practical session in which the instructor and participants build, step by step, financial applications that leverage LLMs and LLM agents.

The course covers the technical foundations of LLMs (tokenization, attention, the Transformer architecture, pre-training and fine-tuning), the design of agentic workflows in which a model plans, calls tools, retrieves documents and executes code, and three applied areas: business valuation, credit risk and portfolio management.

Throughout, the course emphasises rigorous evaluation, the limitations of LLMs (hallucinations, look-ahead bias, calibration) and the ethical and regulatory considerations of using them in Finance.

Students will receive all the material required to set up a modern agentic coding environment on their own computers, including step-by-step instructions to install and configure Claude Code or Cline, together with the slides, lecture notes, code and datasets used in the course.

Teaching Faculty

Who is this course for?

This course is designed for:

Professionals in finance, data science, and management who are interested in learning how to use LLMs in their work
Ph.D. students who want to learn how to incorporate LLMs and agents into their research and methodology

Learning outcomes

Participants of this course will be able to:

Understand how modern LLMs are built and trained, and how architecture, training methods and decoding influence their behaviour on financial text
Set up a working environment and interact with LLMs programmatically using APIs, the Hugging Face ecosystem, and agentic coding assistants
Design and implement agentic workflows in which LLMs plan tasks, use tools, retrieve documents and execute code
Build document-grounded assistants for financial tasks and understand the safety and governance requirements for deployment
Apply LLMs to business valuation, from financial data extraction and cash flow forecasting to discounted cash flow (DCF) valuation and scenario analysis
Use LLMs for qualitative reasoning and deterministic code for numerical calculations
Apply fine-tuning techniques to credit risk assessment and estimate calibrated probabilities of default
Evaluate, govern and deploy LLM-based credit applications in regulated settings
Explore LLM applications in portfolio management, trading and regulatory compliance, using robust backtesting and evaluation methods
Understand the limitations, ethical considerations and regulatory requirements of LLMs in finance, including approaches to mitigating risk

Key topics for Large Language Models in Finance course

Here is a list of topics and themes that will be covered during the course.

Introduction to Large Language Models

Overview of natural language processing (NLP) and text as data in finance
From word embeddings to contextual representations: tokenisation, attention and the Transformer architecture
Pre-training, instruction tuning and reasoning models; sampling and structured outputs
Transfer learning and fine-tuning: LoRA, quantisation and adapting models to financial tasks
Working with LLMs through APIs and open-weight models; hallucinations and retrieval-augmented generation (RAG)
Setting up the Python environment, API keys and agentic coding tools (Claude Code or Cline)

LLM Agents and Workflows in Finance

From prompts to agents: the perceive–reason–act loop, ReAct and self-critique
Tool use and function calling with validated schemas; delegating arithmetic and data access to code
Memory and retrieval: embeddings, vector databases and hybrid search over financial documents
Orchestration: skills, hooks, multi-agent systems and version-controlled agent workflows with Claude Code and Cline
Governance: human-in-the-loop design, audit trails, prompt injection and regulatory constraints

Practical Session I: LLMs for Business Valuation

Extracting financial data from filings using SEC EDGAR and XBRL
Computing and normalising free cash flows; forecasting cash flows with chain-of-thought prompting
Discounted cash flow (DCF) valuation using tool-augmented arithmetic
Scenario analysis and Monte Carlo simulation of valuation uncertainty
Comparable company selection using embeddings
Building an end-to-end valuation pipeline with an agent

Practical Session II: Credit Risk

Credit data foundations, alternative data and regulatory constraints
Fine-tuning a model for credit risk assessment; structured generation and class imbalance
Estimating and calibrating probabilities of default
Using LLMs to simulate household decisions under uncertainty
Evaluation and governance: fairness testing, explainability and model risk management
Deploying an application using a REST API, with monitoring and human oversight

Advanced Topics: Portfolio Management and Future Trends

Portfolio optimisation and estimation error; Black–Litterman with LLM-generated views
LLMs as alternative-data processors: sentiment, language factors and return forecasting
LLM-guided trading signals, backtesting discipline and risk monitoring
Domain-specific and local LLMs: privacy, open-weight models and on-premise deployment
RegTech applications: compliance, anti-money laundering and regulatory text summarisation
Limitations and rigorous evaluation, explainability, ethical considerations and bias mitigation

List of References

The course slides, lecture notes, code and setup instructions will be distributed with the course pack. Some additional references include:

Books

Alammar, J., & Grootendorst, M. (2024). Hands-On Large Language Models: Language Understanding and Generation. O’Reilly Media. ISBN: 9781098150969.
Raschka, S. (2024). Build a Large Language Model (From Scratch). Manning. ISBN: 9781633437166.
Huyen, C. (2025). AI Engineering: Building Applications with Foundation Models. O’Reilly Media. ISBN: 9781098166304.
Lopez-Lira, A. (2024). The Predictive Edge: Outsmart the Market Using Generative AI and ChatGPT in Financial Forecasting. Wiley. ISBN: 9781394242719.
Grimmer, J., Roberts, M. E., & Stewart, B. M. (2022). Text as Data: A New Framework for Machine Learning and the Social Sciences. Princeton University Press. ISBN: 9780691207551.
Schluntz, E., & Zhang, B. (2024, December). Building Effective Agents. Anthropic. https://www.anthropic.com/research/building-effective-agents
Kim, A., Muhn, M., & Nikolaev, V. (2024). Financial Statement Analysis with Large Language Models. Chicago Booth Research Paper. Available on SSRN.
Lopez-Lira, A., & Tang, Y. (2026). Can ChatGPT forecast stock price movements? Return predictability and large language models. Journal of Financial Economics, 184, Article 104335. https://doi.org/10.1016/j.jfineco.2026.104335

Why join our Summer School?

All BSE Summer courses are taught to the same high standard as our Master’s programs. Join us to:

1

Network with like-minded peers

2

Study in vibrant Barcelona

3

Learn from world-renowned faculty

Admissions and Requirements

It is the participant’s responsibility to ensure they meet the admissions criteria.

Next edition: July 5-9, 2027

Early Bird deadline: April 15, 2027

Requirements

Summer School applicants normally demonstrate one or more of the following:

A strong background in Economics or a field closely related to the course topic (Statistics, Law, etc.)
Postgraduate degree or current Master’s/PhD studies related to the course topic
Relevant professional experience

Requirements for Large Language Models in Finance

Participants should have a basic understanding of both Python programming and finance. This ensures that they can effectively engage with the technical and financial applications of Large Language Models (LLMs) covered in the course

Schedule

Here is your schedule for this edition of BSE Data Science in Finance Summer School, Large Language Models in Finance course.

Time

5

mon

6

tue

7

wed

8

thu

9

fri

11:30 - 13:30

Lecture

16:15 - 17:45

Practical

Credit Transfers (ECTS)

To be eligible for credit transfer, students must complete a final project. Students will deliver a short final project one week after the summer school finishes. It will consist in solving a final problem that will include the practical and empirical issues worked on in class.

Please consult the Summer School Admissions page for more information about this option.

Certificate of Attendance

Participants who attend more than 80% of the course will receive a Certificate of Attendance, free of charge.

Course

Large Language Models in Finance

Machine Learning for Financial Risk Management

Modality

Face-to-face

Total Hours

17.5

ECTS

1

Regular Fee

€1,470

Reduced Fee*

€840

*Reduced Fee applies for PhD or Master’s students, Alumni of BSE Master’s programs, and participants who are unemployed.

Multiple discounts are available.

For more information on discounts for participants funding their own course, please click here.

For more information on discounts for companies and institutions enrolling their employees, please click here.

Full discount conditions are available here.

FAQ

Need more information? Check out our most commonly asked questions or contact our Admissions Team.

Can I see the full Summer School calendar?

You can view the full Summer School calendar here.

Is accommodation included in the course fee?

Unfortunately, accommodation is not included in the course fee. Participants are responsible for finding accommodation.

Are the sessions recorded?

Sessions will NOT be recorded; however, the materials provided by the professor will be available for a month after the course has finished.

How much does each Summer School course cost?

Fees for each course may vary. Please consult each course page for accurate information.

Are there any discounts available?

Yes, BSE offers a variety of discounts on its Summer School courses. See more information about available discounts or request a personalized discount quote by email.

Can I take more than one course?

Yes! you can combine any of the Summer School courses (schedule permitting). See the full course calendar.

Credit Transfers (ECTS)

To be eligible for credit transfers, students must complete a final project.

Students will deliver a short final project one week after the summer school finishes. It will consist in solving a final problem that will include the practical and empirical issues worked on in class.

Consult the Summer School Admissions page for more information about this option.

Cancelation and Refund Policy

Please consult BSE Summer School policies for more information.

Are there any evening activities during the course?

A social dinner will take place during the week for all participants, and it is free to attend.

Contact our Admissions Team

Mix and match your summer courses!

Remember that you can combine this program with courses in any of the other BSE Summer School programs (schedule permitting). Maximise your learning this summer and take advantage of our multiple-course discount.

Founding Institutions

Distinctions

Quality Transparency Legal Cookie Policy Contact Us Site map