Data
Research Blog Events
About Careers Newsroom Get Started

8 Ways to Use RavenPack’s News Sentiment Data in Fixed Income Markets

This white paper summarises eight different ways in which academics have applied RavenPack’s aggregated news sentiment data to bring knowledge to the bond and credit sphere.

The first three papers we highlight take similar approaches when incorporating macroeconomic news sentiment into corporate and sovereign credit valuation and risk analysis. One paper approaches CDS spread valuation by using news sentiment, while another looks at cross-asset network effects of news propagation. Another paper looks at how aggregate corporate earnings can assist with municipal bond credit valuation.

1. Enhanced Corporate Bond Yield Modelling incorporating Macroeconomic News Sentiment

The first study ‘off the starting line’ looks at bonds issued by Adidas, Deutsche Bank, Munich Re, Santander, BBVA, Enel and Eni. Author Zhixin Cai, of UCL, asks whether news sentiment can help predict changes in corporate risk. The results suggest sentiment, especially when negative, has a forecasting value: “Negative government and firm-specific news sentiment, in general, affect corporate bond yield spreads more.” But even “positive country news sentiment is effective in the recovery period,” says Cai.

2. Macroeconomic News Sentiment: Enhanced Risk Assessment for Sovereign Bonds

The crisis-prone European fixed income market comes under the spotlight in the next study, which asks whether RavenPack sentiment data can add value to forecasting the sovereign spreads of German, British, Italian, Spanish, and French bonds. When sentiment is included in the mix it improves predictions: “Using sentiment news time series as an input variable decreases the RMSE of the one-step-ahead forecast,” says author Christina Erlwein-Sayer, concluding, “we are able to forecast growing risk in bond spreads by including news sentiment information.”

3. Forecasting sovereign bond spreads with macroeconomic news sentiment

German bunds are the subject of the third paper which tests whether RavenPack data can improve the forecasting of bund yields. In almost all of the bund series, negative sentiment proves a strong predictor, with an acceptably low forecasting error; “We are able to enhance the forecast errors in ARIMAX models through incorporating news sentiment series,” says Erlwein-Sayer. “Credit risk of sovereign bonds is therefore monitored more efficiently when news sentiment is taken into account.”

4. News Sentiment and Credit Risk Valuation: Evidence from the CDS Market

Not surprisingly the Credit Default Swap (CDS) market is especially sensitive to bad news, says study four. Fortunately, RavenPack sentiment data can forecast changes in CDS spreads with a high 1.0% statistical significance. There is an especially “strong negative relationship between the sentiment of firm-specific news and CDS spreads,” say the authors. The effect is heightened due to lack of investor knowledge: “we find evidence that the relation between news sentiment and CDS spreads is stronger for firms with higher information asymmetry.”

5. What Economic Factors Underlie Connectedness in Corporate Credit Default Swaps: News vs. Macroeconomic Factors?

The collapse of Bear Stearns in 2008 triggered a domino effect so wide-ranging it set off a global recession, and the interconnectedness of financial markets is the subject of the fifth study employing RavenPack data. Its main focus is the link between CDS and other financial assets - how does a credit event influence other assets and what factors are involved? The authors’ conclusion is that no one factor explains connectedness but news mainly influences “network returns” whilst macroeconomic factors drive “volatility”.

6. The Information Externality of Corporate Financial Information in the Secondary State-Bond Market

The U.S. muni-bond market is the subject of the sixth study. The problem with the market is its “opacity,'' says author Stephanie F. Chang, but one way of getting around that is to look at other publicly available financial data, such as aggregate, state-wide corporate earnings. To this end, RavenPack’s press-release module can be of especial use.

7. The Effect of Credit Rating Changes on Voluntary Disclosure

The question of whether changes to a firm’s credit rating could have an impact on the extent of its voluntary disclosures is the subject of study seven. This uses RavenPack’s coverage of management forecast data in its experiment design. The results suggest a company’s credit rating is negatively correlated to voluntary disclosure, for reasons mostly to do with financing frictions that arise from credit rating changes.

8. CDS Trading and Relationship Lending Dynamics

The final study seeks to measure the impact of the CDS market on related lenders. Could CDS issuance have a measurable impact on active lenders in the sector by providing a hedge against risk? RavenPack is incorporated to aggregate and measure news sentiment for lenders and cross-referenced with CDS issuance. The impact on lenders is overall positive. “Consistent with our expectations, we find that, following CDS initiation on a borrower’s debt, non-relationship lead arrangers are more likely to originate its loans,” say the authors.

Fixed Income Market Events and Sentiment Data

The RavenPack Analytics Platform includes event and sentiment data for a variety of fixed income strategies and markets, including sovereign debt, corporates, emerging markets, and leveraged loans, available via dashboards or our web APIs. info@ravenpack.com to set up a trial.

Request White Paper

Request White Paper

We will process your personal data with the purpose of managing your personal account on RavenPack and offering our services. You can exercise your rights of access, rectification, erasure, restriction of processing, data portability and objection by emailing us at privacy@ravenpack.com. For more information, you can check out our Privacy Policy.

Discover the RavenPack Platform

Choose from over 190 curated datasets covering a variety of different topics.

Explore Now