ESRB publishes a working paper that shows the news as a rich source of data on distressed firm links that drive firm-level and aggregate risks. The authors developed a machine learning methodology that takes text data as input and outputs a data-implied firm network. The news tends to report about links in which a less popular firm is distressed and may contaminate a more popular firm. This constitutes a contagion channel that yields predictable returns and downgrades. Shocks to the degree of news-implied firm connectivity predict increases in aggregate volatilities, credit spreads, default rates, and declines in output. The results of this paper enable the estimation of accurate measures of firm-level and aggregate risks.
The news-implied networks include a vast majority of links recorded in the currently available data sets. In contrast to the currently available networks, however, news-implied networks capture a wider range of firms and links and are available in high frequencies. On an aggregate level, the authors show that news-implied firm networks capture information about contagion and uncertainty effects that drive aggregate outcomes. The first set of results shows that demand-side considerations incite the news to report about firm links that actively transmit risks across firms and lead to contagion. The next set of results shows that the information contained in news-implied firm networks is highly predictive of aggregate outcomes. Finally, the results show that news-implied firm networks capture information that is not contained in alternative networks. All in one, the results of this paper enable the estimation of accurate measures of firm-level and aggregate risks.
Related Link: Working Paper (PDF)
Keywords: Europe, EU, Banking, Securities, Research, Technology, Machine Learning, Fintech, Natural Language Processing, Risk Measurement, Sentiment Analysis, ESRB
ECB published a decision allowing the euro area banks under its direct supervision to exclude certain central bank exposures from the leverage ratio.
ESAs launched a survey seeking feedback on the presentational aspects of product templates under the Sustainable Finance Disclosure Regulation (SFDR or Regulation 2019/2088).
ECB published input of the European System of Central Banks (ESCB) into the EBA feasibility report on reducing the reporting burden for banks in EU.
ECB finalized the guide on assessment methodology for the internal model method for calculating exposure to counterparty credit risk (CCR) and the advanced method for own funds requirements for credit valuation adjustment (A-CVA) risk.
EBA published an Opinion addressed to EC to raise awareness about the opportunity to clarify certain issues related to the definition of credit institution in the upcoming review of the Capital Requirements Directive and Regulation (CRD and CRR).
APRA is consulting on updates to ARS 210.0, the reporting standard that sets out requirements for provision of information on liquidity and funding of an authorized deposit-taking institution.
FED released hypothetical scenarios for a second round of stress tests for banks.
FED is proposing to temporarily revise the capital assessments and stress testing reports (FR Y-14A/Q/M) to implement the changes necessary to conduct stressed analysis in connection with the re-submission of capital plans, using data as of June 30, 2020.
FED adopted a proposal to extend for three years, with revision, the information collection under the market risk capital rule (FR 4201; OMB No. 7100-0314).
EBA published a voluntary online survey seeking input from credit institutions on their practices and future plans for Pillar 3 disclosures on the environmental, social, and governance (ESG) risks.