| June 11, 2013
In this research, we investigate how EURUSD reacts to short and long term changes in macro sentiment between the U.S. and the Eurozone.
Sentiment is measured by assigning scores to macroeconomic and geopolitical events reported in the news.
Overall, we find evidence that the EURUSD overreacts to daily changes in macro sentiment but underreacts to monthly changes.
Overreaction to macro sentiment translates into short-term price reversal
Long-term underreaction leads to observable sentiment driven momentum effects
In this study, we explore additional applications of the RavenPack macro sentiment indicators in the foreign exchange market. Specifically, we test the hypothesis that the value of a currency pair is correlated to the relative strength of sentiment for the economies whose currencies make up the pair. By probing news, we study how the EURUSD reacts to short and long-term changes in macro sentiment between the Eurozone and the U.S over a 3 month trailing period. We focus on the EURUSD currency pair since the Eurozone and the U.S. have similar economic activity and levels of news flow. We measure the relative strength of their economies as the ratio between Eurozone and U.S. sentiment over a trailing 3 month period. To decide whether to buy or sell the EURUSD, we observe the direction of change in their relative sentiment strength.
We propose two trading strategies based on relative strength: (1) a 1-day reversal strategy and (2) a 1-month momentum strategy. The 1-day reversal strategy is based on the daily change of the relative strength indicator and buys or sells EURUSD when the daily change is negative or positive, respectively. The 1-month3 momentum strategy is based on the monthly change of relative strength and buys or sells the EURUSD on positive or negative sentiment change, respectively, holding the position for one month. We find both the 1-day reversal and 1-month momentum strategies to deliver consistent performance during the back-testing period from January 2004 through April 2013.
In the next sections, we review the construction of our macro sentiment indicators for a given economy, evaluate the 1-day reversal strategy and the 1-month momentum strategy, and deliver our conclusions.
Please use your business email. If you don't have one, please email us at email@example.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 firstname.lastname@example.org. For more information, you can
Your request has been recorded and a team member will be in touch soon.
High inflation has returned in developed markets after decades of lying low. In our latest paper, we show how to build an inflation-based asset allocation strategy using sentiment data and we illustrate that sentiment-based strategies outperform models that depend merely on past observed inflation values.
This year's RavenPack Research Symposium brought two intense days of knowledge sharing in London and New York, from 25 top experts in natural language processing, quantitative investing and machine learning. Together, we explored how firms can leverage new language models to generate alpha, better manage risk and respond to calls for more sustainable investment practices.
Human capital is at the heart of value creation. Our latest research demonstrates how unprecedented workforce insights, sourced from over 200 million job postings, can generate more alpha.