Algorithmic trading – do the markets really follow Twitter sentiment?

Twitter trading algorithm

There has been a huge rise in algorithmic trading over the past few years – hugely powerful servers located as near as possible to the fastest internet connection running complicated programs to hide trades or spot patterns and bet against the trades of others. Even home traders can write scripts for auto-trading on the widely used Meta Trader 4.

Kevin Slavin explains it brilliantly in this video.

Algorithmic trading now accounts for the majority of trades on some markets and Reuters recently reported on the ‘Algorithmic arms race‘.

I was bemused to read that hedge funds are having trouble making money in the current climate and are now exploring new ways to improve their algorithms, here’s a quote from the Reuters article:

“Derwent Capital Markets, a London-based hedge fund firm, uses a program that mines millions of comments made on Twitter to ascertain sentiment, examining the results to predict stock movements. Correlating data from social media websites to markets is one of the hottest topics among this year’s quantitative finance students, UCL’s Treleaven said. Several other hedge funds are also studying how they might incorporate such data.”

Social media monitoring for ‘customer sentiment’ is big business in advertising too at the moment – companies like SalesForce’s Radian 6 are working for many brands and monitoring social networks for what customers are saying about them. The difficulty being that much of what is said on Facebook, which is what really counts, is private and not monitored.

But hedge funds basing their algorithm on Twitter sentiment? Is there any evidence that market movements follow Twitter users’ sentiment? Do traders even use Twitter to chat to each other that much?