Google Trends: How Big Data Can Forecast the Stock Market

August 07, 2014
By: Kayla Matthews

The stock market is incredibly complex. Intricate data provides detailed information on global financial decisions. The market is almost like an intimidating foreign language to those not involved in it.

One general trait of stock market mavens is that they know how to use the data available to them to intelligently forecast potential rises or dips in stock. This helpful data can come from a variety of sources, from intelligent analysis of recent news articles to analysis of the big data available on Google (News - Alert) Trends. With Google Trends, it’s entirely possible to use certain information — like what people are searching for most frequently, or which topics are in decline — to forecast the stock market.

Google Trends’ Role in Predictive Insight

Simply perusing Google Trends casually is unlikely to result in very valuable information. But if you know what you’re looking for, as stock market experts often do, then the information can be invaluable. Recent research seems to support this.

"By mining these datasets, we were able to identify a historic link between rises in searches for terms for both business and politics and a subsequent fall in stock market prices," said Warwick Business School professor Suzy Moat, who elaborated on the school's recent study finding that an increase in search volume for topics tends to precede relevant stock market falls.

Google: Search Engine or Crystal Ball?

Although there is precedence to suggest that a rise in Google searches correlates with a fall on the stock market, it’s important to acknowledge that this isn’t always the case. After all, it’s not like the millions of users who search Google daily have a crystal ball beside their computer. But what they do represent is the public’s interest in a topic, which can be substantial determining factor in stock prices relevant to that stock.

For example, the Warwick study found that searches associated with politics or business represented an increased concern regarding the economy. As such, according to Professor Moat, "this may lead to decreased confidence in the value of stocks, resulting in transactions at lower prices.”

Warwick’s Predictive Big Data Strategy

The researchers at Warwick have found that one of the most effective predictive methods to gain valuable data from search trends is monitoring Wikipedia. Specifically, the researchers identify a list of words representing semantic topics and then monitor those words over the course of two to three years, seeing if rises or falls in search engine popularity correlates with rise or falls in stock market prices relevant to that topic. "Complex events such as financial market movements valuable information may be contained in search engine data for keywords with less-obvious semantic connections,” the study reads.

The Research Paper’s Aim

Those interested in reading Warwick Business School’s research paper on the role of predictive big data can do so here. The paper’s summary is as follows:

“Here, we present a method to mine the vast data Internet users create when searching for information online, to identify topics of interest before stock market moves. In an analysis of historic data from 2004 until 2012, we draw on records from the search engine Google and online encyclopedia Wikipedia as well as judgments from the service Amazon Mechanical Turk. We find evidence of links between Internet searches relating to politics or business and subsequent stock market moves. In particular, we find that an increase in search volume for these topics tends to precede stock market falls. We suggest that extensions of these analyses could offer insight into large-scale information flow before a range of real-world events.”

Although the stock market remains very complex, with no “easy” solution to success, it’s becoming increasingly popular knowledge that search data can be used as a predictive element to determine the rise or fall of stock market prices in a specific niche or industry. Whether people are searching more for ways to make sure your data is secure or the current state of the economy can shed light on specific stock market prices, at least in the eyes of alertly intelligent stock market whizzes.




Edited by Adam Brandt