Edge Webinar
Webinar | June 18, 2026
How sentence-level annotation data from earnings call transcripts can be turned into independent, production-ready signals.
We start with Annotations, but most datasets only expose the derived analytics, which necessarily results in some level of information compression. RavenPack Annotations exposes the layer beneath — entity, event, and sentence-level sentiment data, mapped to exact positions in the source text, with embeddings and 20+ years of history.
Join us for this upcoming webinar that looks at how that structure can be used to build signals directly. Using FactSet earnings call transcripts (Q&A sections), we'll cover:
Flesch readability of analyst questions vs. management answers, and the gap between them. A long–short factor on the gap delivers ~440 bps annualized over the past decade.
Sentence-level sentiment, separated for questions and answers. Question sentiment: ~410 bps annualized. Answer sentiment: ~370 bps annualized.
Same dataset, multiple independent signals. The data is available in real time, so research outputs can be taken into production without structural changes.
Peter is the head of data science at RavenPack. Since joining RavenPack in 2008, he's been a pioneer in the field of applied news analytics bringing alternative data insights to the world's top banks and hedge funds. Peter has more than 15 years of experience in quantitative finance with companies such as Standard & Poor's, Credit Suisse First Boston, and Saxo Bank. He holds a Master's degree in Quantitative Finance from Sir John Cass Business School along with an undergraduate degree in Economics from Copenhagen University. Peter is a recognized speaker at quant finance conferences on alternative data and AI.
Please use your business email. If you don't have one, please email us at info@ravenpack.com.
By submitting this form, you agree to RavenPack's terms of service and privacy policy.
We'll send you the joining details ahead of the webinar.