By Saeed Amen, Founder of Cuemacro, for Bloomberg Professional Services.
Bloomberg Terminals sit on many traders’ desks. Typically, they will have screens on there with market charts and a newsfeed which they check throughout the day. Information streaming on those screens is used as part of their decision-making process. Prices are clearly an important input into a trader’s thinking, and so is, of course, an indication of the sentiment in the market.
One big driver for market sentiment is news. We might have company specific news impacting a stock. Alternatively, it could be macro news, such as a Fed statement, which impacts markets more broadly. There could be news related to the politics, which has notably been a significant driver in recent years, as evidenced by the considerable market volatility around the US Presidential Election and Brexit. We can think of many examples of specific news events that impacted markets. If we ignore the news, we could be ignoring a critical factor that can be driving markets.
The notion that news can drive markets is not something new and has been a feature of markets for centuries. However, the sheer quantity of news that is generated every day is bigger than ever. It is impossible for one person to read all the headlines from news articles written daily. One solution is to get a computer to read the news articles in their entirety and aggregate that into a sentiment signal.
Bloomberg produce several datasets of machine readable news, which can either be consumed as it happens via an API or as an end-of-day flat file. The news has been structured into a format to make it easier to consume, with a record for each article. Alongside, the headlines of an article and the body text, there is also additional metadata. There are various timestamps, as well as topic and ticker tags, which are consistent with those on the Bloomberg Terminal. The additional metadata makes it easier to filter news into topics that are most relevant to traders.
How do we translate this news into actual trades? I recently wrote a research paper on this subject. My focus was using the machine-readable dataset consisting of articles from the Bloomberg News wire to create a systematic FX trading strategy.
As a first step, I examined those news articles specifically tagged with currency tickers. I applied natural language processing to their text to get a numerical sentiment score. These sentiment scores were then aggregated into a daily index for each currency. These were then used as building blocks to create sentiment indices for currency pairs.
The trading rule I applied was relatively simple and involved buying a currency pair when its short-term sentiment was strong and selling when it was weak. There are, of course, many other variations that I could have applied, for example, trying to fade extreme moves in longer-term sentiment. As a final step, all the currency crosses were aggregated together into a trading basket to help diversify returns.
The historical risk adjusted returns of the news based basket between 2010 – 2017, were around 0.6, comfortably outperforming a generic trend following strategy in FX over the same period. Importantly, the correlation with trend following, which is a common approach to trading FX, was very low. This suggests that a news-based approach to trading FX can help diversify returns for investors exposed to trend-based strategies.
As well as understanding the directional move in prices, news can also be used to better model volatility. As part of my paper, I examined the relationship between news volume and volatility in the FX market. I found there was a significant statistical relationship between news volume and volatility. As volume climbs, so does volatility (and vice versa). This relationship seems intuitive. I also did some event studies around FOMC and ECB meetings. There was a reasonable relationship between market chatter around these rate meetings and also the market volatility.
Whilst my paper was specifically about using machine readable news as an input into a systemic trading strategy, it is likely that machine readable news could be just as useful for discretionary traders. As opposed to creating a systematic trading rule from news based sentiment indicators, instead discretionary traders could use such indicators as an input into their decision making process.
More traders have started to use machine readable news. I suspect in the coming years, it will become more established, as market participants realize the value of including it within their investment process.
Saeed Amen is the founder of Cuemacro. Over the past decade, Saeed Amen has developed systematic trading strategies at major investment banks including Lehman Brothers and Nomura. Independently, he is also a systematic FX trader, running a proprietary trading book trading liquid G10 FX, since 2013. He is also the author of Trading Thalesians: What the ancient world can teach us about trading today (Palgrave Macmillan). Through Cuemacro, he now consults and publishes research for clients in the area of systematic trading. His clients have included major quant funds and data companies such as RavenPack and TIM Group. He is also a co-founder of the Thalesians.