Mining the Gap: Extracting Firms’ Inflation Expectations From Earnings Calls
IMF Working Papers, October 4, 2023
Source details
- Canonical URL
- Mining the Gap: Extracting Firms’ Inflation Expectations From Earnings Calls
Other formats
Bibliographic details
- Authors: Silvia Albrizio, Allan Dizioli, Pedro Vitale Simon
- Published: October 4, 2023
- Series: IMF Working Papers
- DOI: https://doi.org/10.5089/9798400253522.001
Methodology
- Construct a new cross-country index of firms' inflation expectations using a novel approach involving natural language processing (NLP) algorithms.
- Index is built from earnings call transcripts.
- The method outperforms other NLP algorithms.
- Keywords and technical terms used in the study include: Artificial intelligence, Natural Language processing, GPT3.5, expectation index, expectations disagreement, firms attention.
Validation and Robustness
- The index has a high correlation with existing survey-based measures of firms' inflation expectations.
- The index is robust to external validation tests.
Key Findings (aggregate-level)
- In an application of the index to United States data, higher expected inflation translates into future inflation.
- The index provides a cross-country measure of firms' inflation expectations.
Firm-level Findings
- Firms' inflation expectations display departures from a rational framework.
- Firms' attention to the central enhances monetary policy effectiveness.
- Analysis leverages firms’ earnings calls transcripts to obtain firm-level dimensions of inflation expectations.
Policy Implications
- Firms’ attention to central (presumably central bank or central announcements) enhances monetary policy effectiveness, implying attention channels matter for transmission of policy.
Content in this bundle
- Working Paper