research Market Intelligence /marketintelligence/en/news-insights/research/hanging-on-every-negative-word-natural-language-processing-analysis-of-credit-rating-action-reports content esgSubNav
In This List
Research

Hanging on Every Negative Word: Natural Language Processing Analysis of Credit Rating Action Reports

Blog

The Party is Over: Tupperware’s Failure

Podcast

Private Markets 360 - Episode 17: European Credit Opportunities

Blog

Engineering and Construction Cost Indicator declined in September as cost increases for materials and equipment moderate

Podcast

Next in Tech | Ep. 186: B2B Payments Technology and Markets


Hanging on Every Negative Word: Natural Language Processing Analysis of Credit Rating Action Reports

Download the full report
Click Here

Credit ratings are opinions about credit risk. When a credit rating changes, the analyst explains why, in a report. The ‘why’ is important. For an equity investor, a downgrade due to a rapid decline in a company’s sales has a negative implication; whereas, a downgrade due to an increase in leverage arising from a share buyback program may be viewed as positive.

This study finds that the relative size of the price impact following a downgrade is dependent on the magnitude of the tone and the topics of focus in the report (Figure 1). Downgrades with strong negative sentiment underperform downgrades with positive sentiment by 2.7% over the following month.

Key findings include:

  • A basket of companies that have been downgraded over the past 3-months (monthly rebalance) with strong negative tone in the accompanying analyst report underperforms the equivalent basket that disregards tone, by 49 bps significant at the 1% level.
  • Analyst reports with strong negative sentiment focus more on the firm’s operating performance; whereas reports with less negative tone focus more on the firm’s use of capital. Specifically, strongly negative reports focus more on sales deterioration, default risk, and negative cash flows. Less negative reports focus more on share repurchase and a company’s use of cash.

Figure 1: Return Comparison of Company Downgrades by Magnitude of Credit Report Sentiment, Russell 3000, 2003 - 2021.

 

*The return of strong negative sentiment is different from the return of positive sentiment at the 1% level.

Source: S&P Global Market Intelligence Quantamental Research. For all exhibits, all returns, and indices are unmanaged, statistical composites and their returns do not include payment of any sales charges or fees an investor would pay to purchase the securities they represent. Such costs would lower performance. It is not possible to invest directly in an index. Past performance is not a guarantee of future results.
Data as at 03/31/2022.

Hanging on Every Negative Word: Natural Language Processing Analysis of Credit Rating Action Reports

CLICK HERE

Using Credit Ratings Research to Filter Important Signals from Noise in News Headlines

Read Article
Learn more about Market Intelligence
Request Demo