Can Wikipedia predict the stock market? Computer says yes
Researchers from Warwick Business School in the UK and Boston University in the US used historical analysis of the site’s data to show that how often financially-related articles on Wikipedia were viewed was linked to future ups and downs in the Dow Jones Industrial Average.
The study looked at the frequency with which 30 pages that described companies in the index like Procter & Gamble, Bank of America and the Walt Disney Company were viewed and edited, between December 2007 and April 2012.
The findings found that increased views of these pages on Wikipedia were linked to falls in stock market prices.
The researchers then found that a simple trading strategy based on the views of those 30 pages related to Dow companies would have led to “significant profits” of up to 141%.
A similar strategy based on views of 285 Wikipedia pages on general financial topics would have led to staggering profits of up to 297%.
A buy and hold strategy, the researchers said, would have only brought in 3% profit.
Dr Suzy Moat of Warwick Business School said: “We know that humans are more concerned about losing £5 than they are about missing an opportunity to gain £5.
“If investors spend more time and effort gathering information before making what they consider to be a bigger decision, then we might expect to see people looking for more financial information before stocks are sold at lower prices, in line with our results.”
The same researchers also found that Google Trends and Twitter can also be indicators of stock market movements.