Recent developments in Artificial Intelligence have led to the introduction of advanced Large Language Models, such as OpenAI’s GPT4 and Google’s Bard. These new machine learning tools promise to revolutionize the way in which millions of people work. For researchers, these models provide the opportunity to tackle challenging questions that require the use of unstructured data, such as text and images. The Large Language Models and Machine Learning for Unstructured Data Seminar, organized by IESE and the Fundación Ramón Areces, is aimed at introducing methods for the analysis of unstructured data to an audience of academics and researchers in the fields of finance, economics and accounting.

An outline of the course structure and objectives:

• The course will begin with an overview of Large Language Models: we will discuss the structure, design choices, and fitting of these models.
• We will then cover machine learning methods for non-textual unstructured data, such as images and audio data.
• Finally, we will focus on how machine learning models for unstructured data can be leveraged to gain insights into econometric parameters of interest. We will overview the theoretical advances in causal inference, complemented by a review of practical applications.
• Coding will be done in Python. Knowledge of Python is not required, and we will provide extra materials and in-class support on coding for participants.
• Finally, we will discuss how these methods are employed in empirical research in economics, accounting, and finance.

The seminar forms part of IESE’s Center for International Finance (CIF), which advocates a multidisciplinary approach to generate and disseminate knowledge and promotes best practices in financial institutions and capital markets.