Stocktwits as Predictor…Research Says Yes!

I have long felt a legal insider advantage being tapped into the Stocktwits stream of consciousness. The data is starting to back me up.

I believe Twitter has won the news business and have said that since 2007. One of the reasons I was so excited to build Stocktwits was to give people that love stocks a platform to talk about stocks all day and a platform to share in real time if they so choose. I was not thinking about ads or investor relations or data. Of course, once you have investors you must think about how all this fits together so please let’s not kid ourselves.

It’s impossible to predict when a ‘plane will land on the Hudson’. Market moving news is breaking all the time. CNBC was running informercials last Sunday (every Sunday) when Apple declared they would be doing something with their cash. On Stocktwits, there was a home for people to flesh it out. A huge network to speculate, digest and position themselves. I would further speculate (give the data and researchers some time) that the social and connected people web is dampening long-term volatility. Information leads to a calmness, a serenity, but that is for another post when the data hounds prove me right.

Over the past 18 months, there has been a growing body of research exploring whether the river of ‘tweets’ produced by Twitter has predictive value with the stock market.

In October 2010, Bollen and colleagues published a study entitled Twitter mood predicts the stock market which suggests that measurements of the collective mood states derived from the analysis of large scale Twitter feeds did just that.

Soon after, Derwent Capital raised $40 million and launched a hedge fund incorporating Twitter sentiment analysis as a component of the investing strategy based on Bollen et al.’s methodology (this was just genius first mover marketing, even if they are making this stuff up…kudos).

Much more recently, Chong Oh and Olivia R Lui Sheng published a study entitled Investigating Predictive Power of Stock Micro Blog Sentiment in Forecasting Stock Price Directional Movement which utilized StockTwits messages exclusively.

The StockTwits data is solely focused on markets and highly organized as StockTwits messages are tagged by stock tickers using the StockTwits $ cashtag and members are expressly focused on market analysis, trades, news and links.

Hence, more signal, less noise.

Utilizing the StockTwits data, Oh and Sheng concluded that,

…investor sentiment as expressed in stock micro blog postings does appear to have strong predictive value for future market directions.

They also suggested that the StockTwits messaging format contributed to their ability to derive significant results, stating,

We establish that the stock micro blog with its succinctness, high volume and real-time features do have predictive power over future stock price movements.

Having participated in and closely observed the StockTwits stream since the beginning, I am not surprised by the researchers’ findings. The crowdsourced nature of the StockTwits stream zeros in on and amplifies new information and analysis so quickly that often we see a stock ticker begin to trend before the majority of a corresponding move in the stock occurs.

Oh and Sheng’s work supports the underreaction hypothesis, a much studied and popular proposal among behavioral economists, which posits that asset prices tend to underreact to new information and only slowly drift over time towards new values which account for the news.

Its my suspicion that as research moves from academia to quantitative analysis performed by money managers, they will discover a variety of anomalies, only some of which might be explained by underreaction.

Tim Richards at The Psy-Fi Blog penned a thoughtful summary of the research and wrote,

I don’t know if StockTwits sentiment analysis can really predict market movements over any time period, but I will make a prediction. Someone, somewhere, is building a system to trade on the possibility. It’s an arms race, and in arms races its usually the side with the deepest pockets and the smartest people that wins. Only, in a world of globally networked social media it’s not so obvious who that’s going to be.

You betcha Tim!



  1. Pingback: Monday links: a dangerous response | Abnormal Returns
  2. ivanhoff says:

    Good points. After all, we are not trading stocks, we are trading other people’s perceptions about stocks. 

    Utilizing social data is a form of second-level thinking.

  3. Pingback: Stocktwits as Predictor [howardlindzon] « Mktgeist blog
  4. Pingback: Monday links: a dangerous response

Comments are closed.