- This blog introduces a trading signal based on sentiment extracted from global newspaper narrative.
- This sentiment-based equity long/short strategy generated 37% p.a. since 2015.
- This sentiment-based signal has been a great tail hedge during the pandemic in 2020.
In this blog, I am leveraging sentiment extracted from global newspapers as leading indicators that anticipate changes in equity markets.
Stock markets are driven by a multitude of factors, whose importance varies over time. While very diverse views and beliefs about stock market movements make it impossible to accurately forecast future prices, price moves can be estimated. Theoretical frameworks explain how observed external factors cause prices to deviate from their assumptions. However, traditional quantitative approaches struggle to explain unexpected variations in prices. News narrative and sentiment contains a wealth of information that may not be fully reflected in the stock market yet. Numerous studies stressed the importance of information from news, showing that sentiment derived from news narrative can be useful for predicting stock market returns.
Global newspaper articles are filtered for content relating to financial markets and the economy, then, the average sentiment score is derived. My analysis is based on big data, natural language processing and machine learning and takes into consideration c 47,000 different news sources that published over one billion news articles since 2015.
Sentiment as leading indicator for market movements
The below chart shows the average tone from newspapers for four countries while the vertical lines denote the date at which the first 100 COVID-19 cases were confirmed for a country. This visualization shows clearly that the average tone for each country declined as the virus spread across the globe.
The trading rule is very simple indeed: go long S&P500, Dax and Nikkei equity futures if the one month change in sentiment is positive, else short, assuming a four day holding period, one day implementation lag, 2bps trading costs; positions are equal-weighted.
Since 2015, this strategy generated 36.81 % p.a. with a maximum drawdown of -4.22% and a sharpe ratio of 2.55. Notably, the signal captured the dynamics during the pandemic in spring 2020 very well which is rather impressive as most systematic strategies struggled during that period.
Sentiment-based signals boost portfolio returns
The results support the hypothesis that news narrative has a causal relationship with financial markets. Incorporating news sentiment into trading strategies can enhance portfolio returns, especially during market turning points where conventional systematic trading strategies tend to suffer.
The latest signal as of 5th March 2021:
Go long S&P500 and Dax equity futures, short Nikkei futures.
Data source: gdeltproject.org
Do not hesitate to contact me with (constructive) comments, questions and suggestions!
Seeking Alpha's Disclosure: Past performance is no guarantee of future results. No recommendation or advice is being given as to whether any investment is suitable for a particular investor. Any views or opinions expressed above may not reflect those of Seeking Alpha as a whole. Seeking Alpha is not a licensed securities dealer, broker or US investment adviser or investment bank. Our analysts are third party authors that include both professional investors and individual investors who may not be licensed or certified by any institute or regulatory body.