Natural Language Processing for Business and Finance

The course will cover – among others – the following topics:

• Introduction to Natural Language Processing (NLP)
• Introduction to Machine Learning  
• Basic Python programming
• Overview of NLP applications most relevant to business and finance 

Over the past few years, thanks to the impressive capabilities of large language models (LLMs), the automatic analysis and generation of (unstructured) textual data has seen rapid adoption in the corporate world across departments, ranging from communications and marketing to finance. In communications, according to a recent survey (USC Annenberg Center for Public Relations 2024) most communication professionals use LLM- powered AI for content generation and increasingly adopt NLP based dialogical interfaces for interacting with data. In finance, NLP powers the use of textual data for research and market intelligence and contributes to the development of FinTech products and services. It is therefore indispensable for future professionals in communication, marketing, finance and other areas to understand how such methods, stemming from the field of natural language processing (NLP), work, how they can help accelerate analysis and content creation in business and financial contexts, and where their limitations and risks lie. This course, especially targeted to students in Financial Communication, but appealing to a broader audience of finance and business students, aims to provide students that do not have a technical background the basic understanding to critically assess NLP tools and their outputs.  It will also give them hands-on experience that will prepare them for a job market in which specialists in financial communication will need to be able to collaborate in interdisciplinary teams with NLP experts and data scientists to harness the potential of NLP technologies for a wide variety of tasks. 

• Quality education
• Decent work and economic growth
• Industry, innovation and infrastructure

In presence

Each class is composed of a lecture and a hands-on session, in which students gain deeper understanding of theoretical concepts by means of running code or doing other exercises.  

Students should bring a laptop to all classes. 

The final grade is composed of graded exercises (40%) and a written exam (60%).