ALGORITHMIC FX TRADING
media, Tomson Reuters now includes sentiment analysis for FX-related news events, measuring the emotional indicators of news and social media content across different topics as a way to help forecast and predict currency trends, according to Rich Brown, global head, quant and event driven trading solutions at Tomson Reuters.
MarketPsych Indices have taken Tomson Reuters service to the next level, addressing sentiment and not only applying it to individual companies but also applying it to a sector (such as tech stocks) and then by market and country, says Brown. Similarly the service measures the amount of interest in certain topics per country, such as the level of uncertainty, stress or urgency in certain currencies. “For example, what is the current level of fear in Greece and how might this affect long and short term currency rates in FX? It helps to draw some comparison of sentiment between different countries and currencies.”
Beyond traditional sentiment analysis, behavioural finance is an increasingly important factor in financial markets and Tomson Reuters’ MarketPsych Indices detect certain emotions that could lead to cognitive bias in investment decisions – for example, what level of fear, joy, uncertainty and confidence is evident. One factor of particular interest is the Market Risk Index or ‘bubbleometer’ as Brown calls it, which aims to detect the level of speculation in news and social media. “Te more speculative the commentary, as a whole is, the more likely it is that we’re in a bubble - and bubbles have a propensity to pop. One can also track the level of financial gloom in Greece, or confidence in Japan to make judgments on the effect it will have on the market structure. It may not directly predict price movements but it can give an insight into the market regime and whether the market is overly optimistic, for example. For FX it is about looking at the sentiment and psychological metrics of each currency and how they correlate with the movements in price.”
Another big change in the last five years of MRN has been the increasing importance of low latency, especially for scheduled events. “If you are a proprietary trader, you need that data as quick as possible. Typically the data is being sourced from multiple providers, as many as five perhaps, and traders will want to check that those numbers match
114 | july 2012 e-FOREX
up. So this is putting increasing pressure on the data providers because there are now comprehensive benchmarks for speed and accuracy,” says Brown. Tis pressure has led to a greater focus on the MRN providers forging exclusive arrangements with some data providers to ensure that they are able to release market information ahead of their competitors.
But whereas the structured news announcements will be increasingly focused on low latency and exclusive arrangements, there will be more room for innovation in the unstructured news space, however this may not yet include social media, the influence of which, says Brown, has not been as great as one might expect. “No-one is going to structure an event-based trading strategy on every tweet. Tere may be certain events that break on Twitter but most traders will find it more helpful to look at longer-term trends. Tere is also the task of separating the noise from the news and ascertaining whether it is a substantive, market-moving piece of information.”
Consequently, says Brown, the MRN market in FX will still be chiefly concerned with structured data. “In terms of making more strategic trading decisions and looking
at the context of news, there is a large opportunity for growth as you look
to see how you can summarise the speeches and the sentiments involved, such as consumer confidence, and then make quantitative assessments.”
Conclusion
Te adoption of MRN beyond economic data points in the FX world still lags behind the equities world. It is still a niche market so there is room for further development. But as providers start to try different ideas, they have to consider how much the market can actually absorb and what services they can truly utilise, says Brown. “As sophisticated as some of these services are, they key to greater adoption may lie in simplifying these services and using visualisation as a means of tracking sentiment rather than taking thousands of feeds on company announcements. Tis is a way to take all the complex MRN capability and put it into the hands of humans so that they can put this information into better perspective in terms of overall trading strategies. So it is possible to pursue both ends of the market – the high frequency, black box traders and also the more traditional traders.”
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103 |
Page 104 |
Page 105 |
Page 106 |
Page 107 |
Page 108 |
Page 109 |
Page 110 |
Page 111 |
Page 112 |
Page 113 |
Page 114 |
Page 115 |
Page 116 |
Page 117 |
Page 118 |
Page 119 |
Page 120 |
Page 121 |
Page 122 |
Page 123 |
Page 124 |
Page 125 |
Page 126 |
Page 127 |
Page 128 |
Page 129 |
Page 130 |
Page 131 |
Page 132 |
Page 133 |
Page 134 |
Page 135 |
Page 136 |
Page 137 |
Page 138 |
Page 139 |
Page 140 |
Page 141 |
Page 142 |
Page 143 |
Page 144 |
Page 145 |
Page 146 |
Page 147 |
Page 148 |
Page 149 |
Page 150 |
Page 151 |
Page 152 |
Page 153 |
Page 154 |
Page 155 |
Page 156 |
Page 157 |
Page 158 |
Page 159 |
Page 160 |
Page 161 |
Page 162 |
Page 163 |
Page 164 |
Page 165 |
Page 166 |
Page 167 |
Page 168