Data
Research Blog Events
About Careers Newsroom Get Started

J.P. Morgan: Using RavenPack Sentiment for Cross Asset Style Timing

Our Chief Data Scientist comments a recent J.P. Morgan white paper which proposes a framework for style timing in cross-asset risk, using various Machine Learning techniques to generate views on expected returns. He highlights where RavenPack data provide the most value.

About the J.P. Morgan report on Style Timing

Style timing has always been a hot topic among institutional investors. This is supported by the evidence that factors (or styles) deliver disparate performance under different macroeconomic regimes. As an example, low volatility stocks are often expected to outperform more volatile stocks in times of recession. However, while this seems intuitive, timing factors and risk premia using a systematic approach is not easy.

In a recent report titled "A Quantitative Framework for Cross Asset Style Timing - Machine Learning, Macro and Time-Series models providing views for Portfolio Tilting", J.P. Morgan proposed a framework for style timing in cross-asset risk premia, which uses various Machine Learning techniques to generate views on expected returns. After applying the Black-Litterman model, these views were translated into tactical portfolio tilts.

To sift through hundreds of predictors, J.P. Morgan considered Machine Learning models from basic stepwise selection models and penalized regression models to ensemble models such as Random Forest and Gradient Boosting. Predictors included historical returns, macro-economic variables, flow and positioning data, J.P. Morgan surveys, and news sentiment from RavenPack.

How does JP Morgan use RavenPack sentiment data

In particular, they utilized the RavenPack event taxonomy that automatically tags news stories with various topics and groups such as economy, employment, inflation, initial offerings etc., to capture high-frequency daily sentiment. Filtering on RavenPack’s fact-level score, they were able to focus on articles that contained sentiment on outlook and expectations that can be expected to be more forward-looking.

J.P. Morgan created RavenPack predictors focusing on:

  • Business & Consumer Confidence
  • US Employment Sentiment
  • Economic Outlook
  • Inflation Outlook
  • Equity Outlook
  • IPO Sentiment
  • Commodity Sentiment
  • Corporate Credit Sentiment
  • Sovereign Credit Sentiment

Where does RavenPack data provide the most value?

Access the full commentaries from Peter on the Style Timing white paper from J.P. Morgan to see more details.

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 180 curated datasets covering a variety of different topics.

Explore Now