Industrial Research Projects

Industrial Research:

RMI has several ongoing industrial research collaborations. There are a few research areas RMI is actively engaging in:

  1. Modeling extreme interdependencies among financial assets for portfolio construction and risk management.
  2. Employing natural language processing and machine learning tools for extracting useful information from business descriptions, earnings reports, earnings conference call transcripts of listed firms for risk identification and decomposition as well as industry classification.
  3. Quantifying ESG and competitiveness measures for listed companies in the regional markets.
  4. Modeling tail risks in a supply chain.

2020

2020-01 H. Gao, J. He and K. Chen; Exploring Machining Learning Techniques for Text-Based Industry Classification.

2022

2022-01 C. Cao and K. Chen; The Scheweinler-Wigner Orthogonalization for Risk Model Construction.

The Global Credit Project: A New Approach to Measuring Stability Risks Around the Globe

The Global Credit Project aims to fill a critical gap in our understanding of how risks in credit markets interact with the real economy. While household debt has been widely studied since the 2007–08 crisis, corporate debt—particularly how and where it flows—remains less understood. Yet growing concerns about corporate borrowing worldwide, from soaring real estate defaults to rising leverage in some industries, underscore the need for better cross-country data and timely analysis.

Building on a decade-long archival effort, the project has assembled an unprecedented dataset on credit flows by economic sector for 117 countries since 1940. Initial findings (published in the Review of Economic Studies) show that which industries receive credit is highly indicative of whether a country is likely to experience a recession or systemic financial crisis. Now, the project will significantly expand and update this dataset through 2022, adding major economies that were previously missing (e.g., China, France, the Netherlands, Sweden, and the U.S.).

Two major enhancements are planned:

  1. Extending Sectoral Credit Data: By setting up a process for data collection from national authorities and integrating these sources in real time, the project aims to keep the global database current and accessible. This will allow policymakers, researchers, and risk managers to spot early warning signs of unsustainable credit growth.
  2. Measuring Credit Conditions: Beyond the volume of credit, the team will compile indicators such as credit spreads, term spreads, and loan maturities from large-scale market databases. Advanced statistical methods will help overcome data sparseness, making it feasible to track credit conditions across countries.

Ultimately, the Global Credit Project will shed light on the link between corporate debt dynamics, GDP growth and crisis risks. This work will inform central bankers, regulators, and financial institutions seeking to manage and mitigate credit-related vulnerabilities worldwide. The project will also result in multiple peer-reviewed publications in leading economics and finance journals.

https://www.globalmacrodata.com/

Acknowledgments

The development of the Global Macro Database would not have been possible without the generous funding provided by the Singapore Ministry of Education (MOE) through the PYP grants (WBS A-0003319-01-00 and A-0003319-02-00), a Tier 1 grant (A-8001749-00-00), and the NUS Risk Management Institute (A-8002360-00-00). This financial support laid the foundation for the successful completion of this extensive project.