ALGORITHMIC FX TRADING
>>> Automated plus manual
Some firms using MRN services in their trading strategies still have a combined automated and manual process in the case of events that are difficult to fully automate. “Tere is still a manual element involved in many firms,” says Terpstra. “When it comes to geo-political events, the more sophisticated firms are generating automated news alerts which can then be interpreted by a human to assess what’s happening and interact with the automated news feed.”
Ryan Terpstra
“In the FX world, economic events are robust and reliable news sources while geo-political events are more challenging because they are not timetabled or recurring events.”
side of the trade, as is the accuracy of information. “Traders also want precise calendar information and timing as to when an announcement will come out, down to the millisecond level.”
Tey also want strong forecasts and estimates leading up to an event because their strategies are based on trading the expected against the actual. Te reliability of estimates can vary depending on the event type and source, says Terpstra. “For example, economic data sources are relatively reliable, while corporate events are more challenging to estimate. In the FX world, economic events are robust and reliable news sources while geo-political events are more challenging because they are not timetabled or recurring events.”
Social media is hard to ignore in this day and age, but Terpstra says it is still in its infancy in terms of its use in FX algos. “I don’t know if many FX firms are using social media in their MRN-based algos, but there are plenty of firms, automated market-makers especially, that are experimenting with it. If they see a lot of chatter around a particular symbol, they may widen their spreads until they can get a human trader to look at what is happening in the market.”
108 | july 2012 e-FOREX
Te biggest challenge with geo-political events, says Terpstra, is understanding the context and the different implications of a single event – a complex task for a machine to perform and one where human intervention is still deemed necessary. “But while these events are a technical challenge, they also represent great trading opportunities because the market movements can be very sharp, such as when S&P downgraded Spanish sovereign debt. However, I think the current approach of combining automated MRN services with human analysis is a temporary stepping stone. Stronger interpretation by automated means is the future because speed is key in these events and the means to make a greater profit.”
RavenPack is a US-based provider of machine readable news with a focus on the linguistic analysis of high- volume news data. Te service originally focused on the equities market and providing news on 30,000 companies worldwide and then disseminating it according to its relevance, its novelty, the type of event involved and the sentiment expressed. Since then the service has spread to other asset classes, such as FX, and further event categories have been included. “We have added ‘location’ to the analysis and we can also detect how events across different places affect currency fluctuations,” says Armando Gonzalez, president, co-founder and chief executive of RavenPack. “If you have a global macro event, like the Tsunami in Japan, then you need to include location in the context of your analysis.”
Growing maturity
Gonzalez says that these new event categories are a sign of maturity in how MRN services are developed and used. “Originally MRN was only concerned with scheduled news events but now we are factoring in unscheduled events such as a Federal Reserve guidance and we can have the algorithms react.” Progress has also been made in terms of tracking sentiment, from the relatively rudimentary approach of analysing the language in a news report to assess how ‘positive’ or ‘negative’ a story might be to more progressive
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