Who is my peer? A novel graph learning approach for peer firm identification

Prof. Yi YANG
Associate Professor
The Hong Kong University of Science and Technology

Date: 29 September 2023 (Friday)
Time: 10:30 am -12:00 pm
Venue: E22-G015
Host: Prof. Yingpeng ZHU, Assistant Professor in Business Intelligence and Analytics
Online registration: https://umac.au1.qualtrics.com/jfe/form/SV_7TByD8YbrgFxWnk


Identifying economically related peer firms is one of the fundamental tasks in academic research and investment decision-making. We propose a novel graph representation learning method to identify economically related peer firms. Our method constructs a firm–analyst bipartite graph and incorporates textual information from firms’ annual filings and analysts’ perceptions of the industry to uncover the underlying relatedness between firms. Our graph learning method is self-supervised in the sense that it builds supervisory signals from the firm–analyst graph topology. We conduct a large-sample empirical experiment and find that our method significantly outperforms existing peer firm identification methods and the traditional GICS6 industry classification in explaining cross-sectional variations in the focal firm’s future stock returns and other financial variables, such as valuation multiples and R&D activities. This study makes a methodological contribution to the literature by addressing an important and longstanding problem in financial economics.


Prof. Yi YANG is an Associate professor in the Department of Information Systems, Business Statistics and Operations Management at Hong Kong University of Science and Technology. He received his PhD in computer science from Northwestern University. His research designs machine learning methods to solve challenging business and Fintech problems. His work has been published in business discipline journals such as Information Systems Research, Management Information Systems Quarterly, Journal of Marketing, Contemporary Accounting Research and INFORMS Journal on Computing. His work has also been published in top-tier machine learning and natural language processing conferences such as Annual Meeting of the Association for Computational Linguistics (ACL), Conference on Empirical Methods in Natural Language Processing (EMNLP) and International Conference on Artificial Intelligence and Statistics (AISTATS).

All are welcome!