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.
How to Construct a News-driven Framework for Forex Day Trading
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.
Forex Events and Sentiment Data
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 here.Request White Paper