You might think a 140 character tweet doesn't have much power, but, as one hedge fund proved, Twitter can help you win the stock market. "Derwent Capital, the hedge fund that is using Twitter sentiment to make its investments, beat the market--and other hedge funds--in its first full month of trading," All Twitter's Lauren Dugan reports. Using an algorithm based on the social media mood that day, the hedge fund predicted the market to make the right trades. Sounds unbelievable that something cluttered with mundane musings and media links could have anything smart to say about the market. But it's working so far.
The idea behind it. Social media is a powerful force in the market--we think it could be making things worse. This algorithm puts those ideas to the test. It's based on a paper that came out of University of Manchester and Indiana University, which found a correlation between mood and Twitter, explains Bloomberg's Jack Jordan.
The number of emotional words on Twitter could be used to predict daily moves in the Dow Jones Industrial Average. A change in emotions expressed online would be followed between two and six days later by a move in the index, the researchers said, and this information let them predict its movements with 87.6 percent accuracy
With such high accuracy, Derwent figured an algorithm that judged Twitter mood would fare well on the floor.
What it actually does. Not all words or moods reflect the markets ebbs and flows. The algorithm specifically looks at the level of calmness on Twitter explains Jordan. "Their results showed that rises and falls in the number of instances of words related to a calm mood could be used to predict the same moves in the Dow’s closing price between two and six days later, with a fall in these “calm” words being followed by a fall in the index. The other moods did not have the same predictive quality, the paper said." Specifically, it looks for words like "alert," "happy," and "vital," adds Financial News' Michelle Price. "Derwent Capital scans a selected 10% of available tweets at random and will then categorise these messages into one of a range of mood states."
But it's not all about the tweets. Understanding the way people are feeling is the underlying principal behind the magic, but other factors ultimately decide what gets traded and how. The algorithm also looks at how the market looks at that moment along with commodities pricing, explains Jordan. "The fund will use algorithms based on the data extracted from Twitter posts and other factors to trade the FTSE 100, FTSE 250 and Dow Jones Industrial Average indexes as well as oil, gold and other precious metals and currencies."
So far the formula has worked. But it's only month one. Maybe next month's tweets will have less predictive powers.
This article is from the archive of our partner The Wire.