Earnings call transcripts also contain soft, non-quantitative information such as sentiment or readability that can be correlated with subsequent market reactions. In addition to providing insights about company performance, earnings calls can offer a window into financial executives' views on past, present and future economic conditions.
In this white paper, we leverage RavenPack Edge event detection and sentiment scoring capabilities to analyze earnings call transcripts and create a real-time Transcript Economic Sentiment Indicator (TESI) for the U.S.
We find that: TESI can identify significant inflection points in the U.S. economic activity and detect meaningful changes in the business cycle. The model accurately detects up to 70% of the U.S. GDP upshifts and 60% of downshifts. TESI-based stock-bond rotation strategies outperform all common static benchmarks on a risk-adjusted basis, with Sharpe Ratios ranging from 0.74 to 0.90 using daily rebalancing and 0.89 to 1.27 when rebalancing monthly. An overlay strategy using combined TESI and ISM Manufacturing PMI-based signals further enhances performance, with the Sharpe Ratio improving from 0.91 to 1.21 when fully rotating between the asset classes based on the signal.
Get the Whitepaper to review how TESI can help to create profitable investment strategies. Download Whitepaper
Request White Paper
We value your privacy