Research Spotlight: Dr Stephen Hansen
31 October 2023
Meet Dr Stephen Hansen, Professor of Economics at UCL Economics. He has recently developed methods for feeding financial transaction data recorded via the everyday activities of millions of consumers into the production of national statistics. Find out more about his research.
What is your role and what does it involve?
I am a professor in the economics department. Currently I teach in the master's program for Data Science and Public Policy, and conduct research that uses unstructured data sets like text and financial transactions to generate new measurement of economic activity and behavior.
What do you find most interesting or enjoyable about your work?
The opportunity to learn something new almost every day of my life.
Tell us about your research
National statistics are currently under heavy pressure. Survey response rates are declining, statistical agencies face real-terms budget cuts, and yet there is increasing demand for granular information. My academic team is collaborating with BBVA, a Spanish-headquartered major international bank, to build national statistics from the ground up using data on billions of individual payments. This provides a template for alternative ways to build economic statistics.
What led you to pursue a research career in this field?
Most data in the world is unstructured, yet until recently this data played almost no role in empirical economics. This seemed like an important challenge to confront. Also, I always had a side interest in programming which made implementing new algorithms fun.
What working achievement or initiative are you most proud of?
Seeing students I supervize move on to successful careers.
What's next on the research horizon for you?
Trying to better integrate the machine learning models that underpin unstructured data analysis with more classical econometric models.
Can you share some interesting work that you read about recently?
The emergence of large language models over the last year. How this will change empirical text analysis in economics is not yet clear, but they present intriguing possibilities.
What would it surprise people to know about you?
I might be happiest in the vast emptiness of the American West... shame there are few economics departments there!