Forex
Marco Jean Aboav | September 02, 2019
In this white paper, news sentiment data aggregated from online financial and economic news sources provides signals for a profitable Forex day trading strategy.
Forex day trading is a notoriously difficult skill to master but could RavenPack’s platform, which uses a bot to read and digest the news at high-speed, help forex day traders make better bets on the direction of foreign exchange rates? This was the question posed in a recent white paper that focused on how news sentiment impacted on three particularly sentiment-sensitive emerging market (EM) currencies: the South African Rand (ZAR), Mexican Peso (MXN) and Turkish Lira (TRY) - all paired with the U.S. Dollar.
The strategy used RavenPack’s average sentiment scores to provide buy and sell signals when news sentiment associated with fundamental drivers for a pair was either positive or negative.
The initial conclusions provided evidence sentiment could indeed be used to successfully predict EM FX direction.
The results showed the strategy correctly forecast USD/ZAR’s direction 55.40% of the time, over of a period of a minute, based on a sample of 99,392 trades, tested out-of-sample (OOS).
“The idea is to consider each news item classified by their sentiment, either positive or negative, to understand the short-term dynamics post-news-release using the XGBoost algorithm for prediction. A simple analysis of the out-of-sample directional accuracy shows the best results are typically within 1 minute from the release with a peak of 55.4% for USDZAR,” says the paper’s author Marco Jean Aboav, Associate Professor in Financial Technology at CASS Business School.
The paper also made a case that sentiment works just as well for longer holding periods, despite the evident difficulty of predicting long-term FX movements.
The research provides a scientific basis for the development of more complex FX trading strategies with the incorporation of other variables potentially further enhancing value for traders.
Easily implement the results of this white paper using the RavenPack Analytics Platform, which includes Forex event and sentiment data on all traded currencies, available via dashboards or our web APIs. Request a trial today.
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.
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.