This page has been archived and commenting is disabled.
Trading Twitter: Where Noise Becomes Signal
Over four years ago when we discussed the high frequency predator traders feasting on the signals of others, few believed it possible (and fewer still comprehended it). Today there is another potential disruptor in US equity market microstructure, the transformation of noise to signal from the overwhelming drivel of a Twitter stream. Macro signals (the hashcrash in April when AP's account was hacked and this week's Israeli military tweet misunderstanding) have had dramatic effects on the market but individual stock trading success remains elusive.
For social media stocks trading, "sentiment" implied from the Twitter stream leads prices by hours according to a recent study, but while tweets can contain useful information – it is far from guaranteed. “You have to be happy with a lot of noise in your data,” one advocate notes, but, as the FT notes, a recent PhD study of the translation of twitter noise to actionable signal perhaps sums it up best, "The proponents of this idea really do exaggerate it... I’m not saying there’s nothing here, but I’m not saying you can print money either."
Of course, the biggest drawback (for now), not even the most advanced language processing algo can comprehend sarcasm.
...traders are starting to look at Twitter not as a buy or sell in itself but as a way to generate hot tips on other stocks.
The idea is a simple one: the 500m daily messages on Twitter put online the sort of gossip usually only available in snippets by eavesdropping in bars or the office lift. Apply some moderately sophisticated computer filtering, and out should pop market-moving news and views investors can use.
Twitter has already demonstrated its potential to move markets, with the “hash crash” – named for the “#” symbols used on the microblogging service – knocking 145 points off the Dow Jones Industrial Average in April on the back of a false tweet from a hacked wire service account.
This week brought another example, with some traders blaming a misunderstood Israeli military tweet referring to bombing Syria in the 1973 war for a $1 per barrel drop in the oil price on Thursday.
...
“You have to be happy with a lot of noise in your data,”
...
The latest attempt to prove that Twitter contains useful information comes from Ilya Zheludev, a PhD student at University College London... “The proponents of this idea really do exaggerate it,” Mr Zheludev says. “If it really was as possible as they think it is, first of all they wouldn’t publicise it and second they would be rolling in cash.”
“I’m not saying there’s nothing here, but I’m not saying you can print money either.”
...
For most stocks there were not enough tweets to generate statistically significant volumes, while for the FTSE and many large companies – including Google, Intel and Bank of America – the sentiment had a stronger link to past price moves than future ones.
But 11 of the 50 financial instruments tested showed a statistically significant link,
...
Joe Gits, founder of Chicago-based Social Media Analytics, says that he expects a turnover of $60m in two years from his system.
...
He has big expectations. “I think it’s going to become every bit as big as earnings estimates in the not-too-distant future,” he says.
...
Previous attempts to trade purely on the back of social media data have come unstuck. Mr Peterson ran a hedge fund based on signals from social media, but gave up after finding it did not work for the biotech sector. In London Derwent Capital set up the first Twitter hedge fund in 2011, but quietly closed down again just a month later.
...
Mr Zheludev’s approach is rather more complex than the simple algorithms used by some early traders to extract signals from the online noise. But even the most advanced language processing has trouble with much of Twitter: they cannot process sarcasm.
Here is Ilya Zheludev presenting his thoughts last year at a TED Talk:
Social media is more than just Facebook updates and Twitter posts. The term also refers to any user-generated online content, from readers' comments on articles in the Financial Times to blog posts. Social media is traditionally seen as just benefiting the end-user: the friends exchanging photos on Facebook. But its value is far greater than that -- the amount of publically accessible data that social media generates is phenomenally large. Just by way of example, there are 6 million Facebook views every minute. Harnessing that largely untouched data correctly has unbelievable implications: we're able to see into the future. We can predict so many facets of life, from the spread of disease to the time and location of the next military uprising. Social media lets us see into the minds of millions, in real time -- something that has never been possible before. The future isn't a great unknown any longer.
Being specifically interested in Finance, Ilya's research is driven by the relationship between the internet's 'mood' and financial markets.
The bottom line is that in a world in which signal is gone courtesy of central planning and where only the Fed's H.4.1 statement (the weekly balance sheet update) matters (as we said back in January 2010); market participants are desperate for any "edge", even if it means creating signal out of pure reactionary noise.
- 12738 reads
- Printer-friendly version
- Send to friend
- advertisements -




Bow before me, not-market-leading cretins!
Oh, great and powerful OZ, you're wish is our command.
Catnip, tuna, and Lauren Lyster's lap
A bunch of generals have been fired at the Pentagon. The reason - some NUKES have been stolen!!! I've looked everywhere and couldn't find A SINGLE WORD about the nukes. Good job, MSM! Goebbels would've been very proud of you, assholes!
The "official" reasons for their firings on the same day range from gambling problems, Bunga-Bunga parties, counterfeit casino chips, but nothing 'bout the phucking stolen nukes...
Looney
P.S. It looks like another False Flag is comin' ;o)
P.P.S. Starngely enough, at the same time a top Russian general have been promoted to head some Nuclear Agency (too difficult to pronounce) ;o)
Well here are some claims about that nuke story, on a quite offbeat website in Ireland
FWIW ... site claims sources in Russian intelligence ...
Says Obama ordered a false flag mini-nuke attack on Charleston USA, generals put the nuke in the ocean instead and caused an earthquake
'Obama Ousts Top Officers After Nuke Explodes In Ocean Instead Of Charleston'
From the famous ... and one and only ... Sorcha Faal
http://www.whatdoesitmean.com/index1714.htm
Well, you'd think if they were gonna disobey orders they'd dropped it off in D.C. before exploding it.
Now talk about an earthquake!
WTF does the prez have against Charleston?
It's a huge Mason/Illuminati city. Google Albert Pike.
Twitter - shmitter...
"not even the most advanced language processing algo can comprehend sarcasm"
Hell half the PEOPLE on Zero Hedge cannot comprehend sarcasm. Poe's law. There's a rumor that there was massive buying in Berkshire Hathaway stock at one time because of a lot of twits chattering about it so something MUST be going on. All the talk was about actress Anne Hathaway.
Actually its was about Anne Hathaway's snatch which she gave the world a good look at while getting out of a car.
http://www.peeperz.com/anne-hathaway-pussy-upskirt/
Twitter at the moment is noisy with people talking about the EBT system being down.
somebody pull the plug, it would be much better dark, this is not light
Yeah, I read this story in the FT Weekend this morning. The way I see it, any algo that can extract a useful signal from the vast Twitter noise is bloody amazing. If anyone can find a bit of edge in that swamp, good luck to them.
(Now I'm wondering whether there are any algos scanning ZH stories/posts...)
Talking about noise-signal, the stats for ZH posts show that only 1-2% of readers post a comment. Does this strike anyone else as odd?
Baaa....
With intelligent comments like this I guess it's just as well more people don't post.
"...they cannot process sarcasm."
O.K., we need to get The Onion to send out their headlines on Twitter anonymously.
This could be the apocalypse! Really!
The computer system controlling welfare SNAP payments has broken down. This is like the old joke about the five words that could bring down the Soviet system: "They are out of vodka".
The food stamp system has failed. The poor will be eating each other by monday. This is worse than the zombie apocalypse.
http://boston.cbslocal.com/2013/10/12/computer-upgrade-blamed-for-nationwide-ebt-system-shutdown-on-saturday/
Well, if the poor will be eating each other by Monday, then you've got about a month to get the hell out of Dodge.
With all the fat assed Merxicans the buffet at the Golden Corral runneth over.
The pizza chains are going to be pissed off!
Local pizza chain prominently displays "EBT Accepted" in their ads and on the storefront.
No lie: two large pepperoni pizza's and a two-liter of soda pop with your EBT card - nutrition at it's finest!
Too bad the markets are closed or you could short Walmart. They line up in the stores to spend their SNAP money when it becomes available at midnight.
Another open system that will be manipulated by people. People use other people's computer to attack, say the Pentagon. One could take a position on a stock and unleash twitter accounts to move the stock. I am no computer/network expert, but even I understand how twitter could be abused so people could steal easy money.
"not even the most advanced language processing algo can comprehend sarcasm."
?
:)
three dimensional oscilloscope....the next tool in the financial markets.
Talking of Twitter, EBT is down, check it out: https://twitter.com/search?q=%23ebt
Carl iCon knows a thing or two about hot stock tips on Twitter...