June 6, 2022
In our latest study, we demonstrate how the risk-adjusted performance of systematic credit investing strategies can be significantly enhanced by incorporating real-time analytics from RavenPack’s Edge news, earnings call transcripts, and insider transactions which offer complementary sources of alpha.
This year is proving to be very challenging for fixed-income investors. With inflation at multi-decade highs globally, interest rates are rising rapidly with a devastating effect on bond prices.
The advent of real-time, machine-readable news over the last decade has paved the way for sentiment-based trading strategies that take advantage of media content as a reliable predictor of individual firm’s financial performance.
In our latest study, we demonstrate how the risk-adjusted performance of systematic credit investing strategies can be significantly enhanced by incorporating real-time analytics from RavenPack’s Edge news, earnings call transcripts, and insider transactions, which offer complementary sources of alpha.
We tilt the long-only U.S. investment-grade benchmark based on senior, unsecured, and liquid bonds since 2015-2022 and find :
When evaluated individually, Earnings News and Transcripts demonstrate complementary performance. The Earnings News strategy performs well over the short-term, with annualized returns of 105bps in excess of the annual investment-grade benchmark (left) for an effective holding period of two days, compared to 14bps for 10 days. With Transcripts, annualized excess returns are the highest at the one-week horizon (58bps compared to 27bps for News).
Complementing the security-selection skills, the combined Earnings Intelligence strategy outperforms the individual signals from Earnings News and Transcripts while decaying at a slower rate than News. The Earnings Intelligence strategy steadily generates benchmark-adjusted Sharpe Ratios (right) of nearly 0.60 at the three-month effective holding period (compared to 0.40 for Earnings News), while adjusted Sharpe Ratios for Transcripts improve from 0.25 to 0.50 as the holding period increases from two weeks to three months.
Significance tests demonstrate that sentiment-tilted portfolios statistically outperform those with random tilts, dominating zero-skill strategies at the 92% (for Earnings News and Transcripts) and 95% (for Earnings Intelligence) confidence intervals.
Annualized returns (left) and Sharpe Ratio (right) in excess of the U.S. investment-grade benchmark, for long-only credit portfolios using different tilting magnitudes and signals. Source: RavenPack, April 2022
Please use your business email. If you don't have one, please email us at info@ravenpack.com.
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.
Your request has been recorded and a team member will be in touch soon.
RavenPack Earnings Intelligence combines signals from separate sources augmented with sentiment and thematic analytics for a powerful alternative that removes the limits of isolated vendor data.
In our latest research paper, we focus specifically on European markets by sequentially overlaying three RavenPack Earnings Intelligence signals.
We consider incorporating sentiment signals from news, earnings call transcripts, and insider transactions to boost the risk-adjusted returns, and revive factor performance.
We find stronger, more predictable market reactions when the words of company executives agree with their actions.
We explore the combination of earnings-related news and earnings call transcripts.
Incorporating Earnings Calls transcript data increases IR to 1.4 for US Mid/Large Caps and 2.3 for Small Caps.