Internship research - Exploring LLMs in financial and code analysis

ABOUT CFM

Founded in 1991, we are a global quantitative and systematic asset management firm applying a scientific approach to finance to develop alternative investment strategies that create value for our clients.
We value innovation, dedication, collaboration, and the ability to make an impact. Together, we create a stimulating environment for talented and passionate experts in research, technology, and business to explore new ideas and challenge existing assumptions.

Overview and goals:

We are offering two opportunities for highly motivated interns to delve into the utilization of Large Language Models (LLMs) in both financial analysis and data coding frameworks. This internship combines two key focus areas, encouraging collaboration and cross-disciplinary learning.

In the financial domain, interns will aim to replicate and extend findings from recent academic research by extracting fundamental insights from analyst reports and corporate communications using LLMs. The first task involves assessing LLMs' ability to perform financial statement analysis based on the study "Financial Statement Analysis with Large Language Models," focusing on balance-sheet data and income statements without narrative context. The second financial task includes extracting stock valuation data and parameters, such as discount rates, from analyst reports, informed by the paper "Valuation Fundamentals."

On the code analysis side, interns will investigate the growing literature on LLM applications for coding, particularly in the areas of fine-tuning, prompt engineering, and agentic AI frameworks. Responsibilities include building Retrieval-Augmented Generation (RAG) systems with open-source models to access and cluster research papers, such as those from ArXiv. Additionally, interns will replicate research papers, starting from simpler examples, using agentic AI frameworks with different LLMs fine-tuned for specific tasks.

This comprehensive internship is ideal for candidates with a keen interest in the intersection of financial analysis and advanced data technologies, equipped with strong Python coding skills and a passion for learning how LLMs can transform information extraction and data clustering tasks.

Required Skills and Qualifications:

• Pursuing a degree in Finance, Economics, Data Science, or a related field
• Familiarity with financial analysis and data management tools
• Basic understanding of LLMs and machine learning concepts
• Proficiency in Python or similar programming languages for data analysis

Duration :

4 to 6 months

Reference:

• Kim, A., Muhn, M., & Nikolaev, V. (2024). Financial statement analysis with large language models. arXiv preprint arXiv:2407.17866.
• H Décaire, P., & Graham, J. R. (2024). Valuation fundamentals. John Robert, Valuation Fundamentals (September 09, 2024).
• Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. D. O., Kaplan, J., ... & Zaremba, W. (2021). Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374.

EQUAL OPPORTUNITIES STATEMENT

We are continuously striving to be an equal opportunity employer and we prohibit any discrimination based on sex, disability, origin, sexual orientation, gender identity, age, race, or religion. We believe that our diversity, breadth of experience, and multiple points of view are among the leading factors in our success.
CFM is a signatory of the Women Empowerment Principles.
 

FOLLOW US

Follow us on Twitter or LinkedIn or visit our website to find out more about CFM.