Fintech
New FinTech course explores language-based artificial intelligence
Finance may be an industry dominated by numbers, but David Papa ’90 believes that words are the key to creating high-performing portfolios.
Investors are increasingly using AI tools to inform their financial decisions, the professor says Finance (and Bentley graduate) explains. He notes that natural language processing (NLP) programs, which recognize and interpret patterns in human speech and text, are proving particularly adept at transforming massive amounts of data, gleaned from earnings call transcripts, annual reports, announcements of acquisitions and other finance-related company data. communications: into actionable information.
This fall, Pope teamed up with colleague Bentley Tamara Babaianprofessor of Computer Information Systems (CIS), to introduce “Investing Applications of Natural Language Processing” (FT 370), an interdisciplinary course that gives students a comprehensive look at the theoretical foundations and practical applications of NLP programs in the financial industry. A required course for students majoring in Financial Technologies (FinTech)features weekly lab sessions that teach students how to create their own machine learning models using Python, a popular programming language.
According to Pope, these hands-on coding sessions set Bentley apart from other universities offering FinTech courses. “Having firsthand experience coding NLP programs gives our graduates a deeper understanding of the technology and its applications, and therefore a competitive advantage,” he explains, noting that the cutting-edge information covered in class is “so new that it they are still not even found in textbooks.” .” Instead, it offers students access to newly published research papers and personal and professional insights: Founder and CEO of Analysis of vocal craftsmanship – a company that uses artificial intelligence to analyze “vocal characteristics imperceptible to the human ear” that reveal the speaker’s “true emotional state and intentions hidden in his words” – Pope has more than 30 years of experience in financial and data analysis.
For the course’s culminating project, he and Babaian assigned students to build their own NLP programs using the Gunning Fog Index (GF), a measure of language complexity based on sentence length and the number of syllables per word. “Executives who use complex language in earnings calls typically do so to obfuscate or delay the release of bad news,” Pope explains, “and as a result, their companies’ stocks underperform.” Based on their program results, students created portfolios with stocks purchased from companies with lower GF ratings (i.e., simpler language in their earnings calls) – portfolios that “would outperform the S&P 1500 by 3.8% every year from January 2011 to June 2023″. ”, he observes.