Machine learning models track trends in financial research

What are the main topics in finance and budgeting? How have they changed? And what future topics should be studied more closely by experts and practitioners?

Can Chen and two of his former doctoral students, Shiyang Xiao of Syracuse University and Boyuan Zhao of Florida International University, used structural topic modeling (STM), a machine learning technique, to explore these topics over the past 40 years. and its dynamics.Articles recently published in magazines public budget and finance.

Chen et al. used STM to identify 15 potential categories in the fields of public budgeting, public finance, and public financial management from the titles and abstracts of 1,028 papers published in the journal from 1981 to 2020. I’ve identified a topic. They compared these topics to those covered in this journal. We found a lot of overlap with the Chartered Financial Officer (CPFO) standard exam. However, some topics that were less frequently mentioned may suggest research questions that have not yet been explored in PB&F.

Chen, an associate professor of public management and policy at the Andrew Young School of Policy Studies, directs the university’s doctoral program. Programs in Public Policy. After he presented this research at the Next Generation Finance Conference hosted by Georgia State University, he received and appreciates the helpful feedback and comments. In his Q&A that follows, Chen reveals more about the journal, his findings, and his motivations for conducting this research with his colleagues.

What made you decide to do this research?

The journal is celebrating its 40th anniversary, so I wanted to do something to commemorate the anniversary and look back at the history of the journal. Another reason is that the methodology we used, machine learning, was new to this publication. Traditionally, articles were reviewed manually. We leveraged technology for smarter reviews.

And more importantly, PhD students sometimes come up to me and ask if I understand what the big trends in the field are. They ask me questions about public budgeting and the big picture of finance because he has to specialize in his first year. What are the main recent topics in this field? This study allows us to look back over 40 years and, more importantly for PhD students, to determine trends throughout its recent history. I did.

Where did you get the idea to use machine learning and text mining to find trends and themes?

When I came to Georgia State University, AYSPS was driving a digital landscape initiative that used big data for analytics. So I thought, “Oh, wow! This is a great methodology. Schools want us to use it.”

While machine learning has been used in other fields to analyze big data sets, such as engineering, science, and technology, our understanding is that our research has been able to utilize machine learning and text mining methodologies in the public budget. It is one of the first research efforts to introduce into the field of organization and finance. This is what we’re all about, using ideas from other fields and applying them to our field.