Can Twitter be used to predict movements in the stock market?
Dutch technology company SNTMNT (“Sentiment”) are betting that it can. They’ve announced the Trading Indicator API, the world’s first API that makes predictions based on Twitter sentiment about future stock price movement for all stocks in the S&P 500.
The API gives hourly and/or daily buy and sell signals by analyzing financial sentiment on Twitter, with SNTMNT’s algorithm stripping out extra noise in asset pricing, and can be used be investors as an additional indicator on top of their normal fundamental and/or technical analysis.
An overview of the API’s methodology can be seen below.
The early signs are good: SNTMNT say that the algorithm’s predictive accuracy can be as high as 60 percent, but are cautious about using social media as a standalone trading tool.
“Anybody who claims that social media can be used as a leading trading signal is fundamentally wrong,” says Vincent van Leeuwen, co-founder of SNTMNT. “The signal-to-noise ratio on social media channels like Twitter is (still) way too low to provide standalone trading signals, let alone a hedge fund, but definitely high enough to provide an innovative trading indicator.”
Of course, SNTMNT aren’t the first company to mine tweets for trading sentiment – Derwent Capital Management raised £25 million from investors and used Twitter to beat the Dow Jones Industrial Average and deliver a two percent return.