Bes Stocks To Buy 2014, Best Stocks For 2014: How Twitter Can Predict the Future of Stock Prices

Wednesday, March 28, 2012

How Twitter Can Predict the Future of Stock Prices

When it comes to the new age of social media, many are skeptical to jump on board. Complaints of too much personal information being released to the public and the constant output of information necessary to keep up with Facebook, Google Plus, and Twitter can weigh heavily on those skeptics decision to give social media a try.

But do you think those skeptics of social media would be more intrigued if they were told that by understanding sites like Twitter, they could make some serious money? Probably.

Well than listen up, investors and Tweeters, alike, because research has shown that Twitter 'predicts' stock prices more accurately than any investment tactic.

A team of scientists from the University of California has created a computer model which allows them to 'predict the future' of the stock market by scanning the massive user-information network.

The team's computer has up to 11% more accuracy than any other computer model. The way it works is the software looks at volumes of Tweets containing references to companies or products across the entire “Twitter-sphere” and how they link to Tweets on other subjects.

What the computer does with that information is where lies the profits. From the information gathered, the computer can predict both the volume of trading and the value of a stock the next day.

Now investors are drooling, and rightfully so.

During a four-month test, the model did better than the Dow Jones Industrial Average and also outperformed other baseline strategies between 1.4% and up to 11%. Perhaps it's not sounding like the massive gains investors thrive for, but to study the pace in which the world's fastest moving social network works, this advantage could be a ! big mone y maker.

In reality, Twitter's lifestyle is quite similar to those investing in the stock market. Passionate investors frequently keep the market figures accessible at all times, and closely pay attention to the closing bell come 4pm each day. Twitter activity picks up speed around 4pm and 5pm each day, while nearly 25% of all users check Twitter several times a day-- like a vested stock market watcher.

The pace of the New York Stock Exchange floor is also rampantly compared to the Twitter-sphere. Over 1,650 Tweets are composed each second, totaling nearly 150 million a day and one billion new Tweets posted every week. Similarly, the rate at which shares are exchanged within the NYSE averages around 100 million each trading day.

Of the 100 Fortune Global Companies, 88 of them post daily news and updates on Twitter, while nearly the same amount are a publicly traded stock and/or the company invests within the stock market.

The similarities between the two are significant, but when used together, a new way to invest is revealed.

From The Daily Mail,

Professor Vagelis Hristidis, who specialises in data mining research which focuses on discovering patterns in large data sets, worked on the model. He said: ‘These findings have the potential to have a big impact on market investors.

‘With so much data available from social media, many investors are looking to sort it out and profit from it.'

Hristidis's team studied how activity on Twitter correlated to stock prices and trading volume on a daily basis. Previous research of Twitter's investment significance only looked at the sentiment shown through Tweets, either positive or negative, about particular stocks and trades. Othe! rs looke d at the overall stock market indexes rather than individual stocks.

But this new research from Hristidis has instead inspected the volume of Tweets, and the way that they are linked to other Tweets, topics or users, in particular with individual stocks.

Here's how one of their latest studies went:

First, they obtained the daily closing price and the number of trades for 150 randomly selected companies in the S&P 500 Index for the first half of 2010. Then, they created filters to select only relevant Tweets for those companies during that time period. For example, if they were looking at companies such as Apple or Caterpillar, they would exclude Tweets focused on the fruit or insect respectively.

The expectation was that the number of trades would correlate with the number of Tweets. But actually, the number of trades was slightly more correlated with the number of “connected components”-- which is the number of posts about distinct topics related to one company.

Since discussion on Twitter does not fall under categories, it's a stream-of-conscious kind of networking, the data had to be siphoned between topics. For example, by using Apple, there would be categories of posts discussing Apple's new (and old) CEO, a new product like the iPad, and its latest earnings report.

The findings showed that a company's stock price slightly correlated with the number of connected components as well.

For the study, the researchers simulated a series of investments between March 1, 2010 and June 30, 2010 and analyzed performance using several investment strategies. During that time frame, the Dow Jones Industrial Average fell 4.2 percent.

The model the researchers developed using Twit! ter data lost on average 2.4 percent.

But Professor Hristidis noted several potential weaknesses in the study including that the trading strategy worked in a period when the Dow Jones dropped, but it may not produce the same results when the Dow Jones is rising.

We might be a few more detailed research studies away from creating a flawless model to assist investors through the powers of Twitter, but for now, the correlations are strikingly impressive.

So the next time you're looking at the stock ticker, perhaps give a search on Twitter for a specific company you had in mind. Your financial gains might actually be something worth Tweeting about.

*Remember (since we're on the subject) to receive the most up-to-date financial and investment information, you can follow us on Twitter @WealthWire.

Related Articles: