Apr

26

 The Chair asked how can one trade the news.

"Big Data Gets Bigger: Now Google Trends Can Predict The Market":

Yesterday three economists, (Tobias Preis of Warwick Business School in the U.K., Helen Susannah Moat of University College London, and H. Eugene Stanley of Boston University) published an eye-opening paper that said Google Trends data was useful in predicting daily price moves in the Dow Jones industrial average, which consists of 30 stocks. Their research result:

An uptick in Google searches on finance terms reliably predicted a fall in stock prices.


"Debt" was the most reliable term for predicting market ups and downs, the researchers found. By going long when "debt" searches dropped and shorting the market when "debt" searches rose, the researchers were able to increase their hypothetical portfolio by 326 percent. (In comparison, a constant buy-and-hold strategy yielded just a 16 percent return.)

This was a 180-degree turnaround from earlier research, by Prof. Preiss published back in 2010.


Back in 2010, he used Google Trends data and found the opposite conclusion:


"The Google data *could not predict the weekly fluctuations in stock prices*. However, the team found a strong correlation between Internet searches for a company's name and its trade volume, the total number of times the stock changed hands over a given week. So, for example, if lots of people were searching for computer manufacturer IBM one week, there would be a lot of trading of IBM stock the following week. But the Google data couldn't predict its price, which is determined by the ratio of shares that are bought and sold."


What happened? Are people revealing more of their investment intentions in their searches?

The clue may be in looking at changes in the nature of what's reported on Google Trends. In a nutshell, the data is getting bigger, by getting finer, and faster.

Also, this is an interesting graph with current downtick in search and uptick in stocks.

Pitt T. Maner III writes: 

More research via Nature which references possibly useful search term analysis:

1) "Quantifying Trading Behavior in Financial Markets Using Google Trends":

'Crises in financial markets affect humans worldwide. Detailed market data on trading decisions reflect some of the complex human behavior that has led to these crises. We suggest that massive new data sources resulting from human interaction with the Internet may offer a new perspective on the behavior of market participants in periods of large market movements. By analyzing changes in Google query volumes for search terms related to finance, we find patterns that may be interpreted as "early warning signs" of stock market moves. Our results illustrate the potential that combining extensive behavioral data sets offers for a better understanding of collective human behavior.'

And a graph using a "Google Trends" Strategy claims to show this:

'Profit and loss for an investment strategy based on the volume of the search term debt, the best performing keyword in our analysis, with Δt = 3 weeks, plotted as a function of time (blue line). This is compared to the "buy and hold" strategy (red line) and the standard deviation of 10,000 simulations using a purely random investment strategy (dashed lines). The Google Trends strategy using the search volume of the term debt would have yielded a profit of 326%.'

2) A reference to Goodhart's Law:

'Furthermore, economists acknowledge that any transparently profitable strategy for playing the markets will quickly lead to a change in trader behaviour that cancels it out — a principle called Goodhart's law, after the British economist Charles Goodhart. "Social systems have the complication that the system may directly react to predictions being made about its behaviour," agrees Susannah Moat, a computational social scientist at University College London and a co-author on the study.'


Comments

Name

Email

Website

Speak your mind

4 Comments so far

  1. Ed on April 26, 2013 4:39 pm

    I would bet that search terms related to finance and investing are directly influenced by recent price behavior of the stock market, much like sentiment indicators typically just reflect recent price action.

    It might be that this is simply another way of looking at the phenomenon that expected return rises after a decline and falls after a rise. I don’t have the statistical chops to do it, but it might be useful to control for this and see if it has any independent predictive value .

  2. Fred Tyler on April 26, 2013 7:03 pm

    I posit that such research is utter nonsense.
    If it was as profitable as the authors claim they would have profited from it instead of making it public.
    There is no such thing as a free lunch.

  3. Jeff Watson on April 27, 2013 8:41 am

    When some very bullish news comes out, and the market yawns at it or vice versa gives one a sense of the strength of the market, and one can make the appropriate trading decision.

  4. Craig Bowles on April 28, 2013 7:43 pm

    Last quarter, going into Apple earnings and PMI data was very tempting time to be bearish and the releases were terrible. The problem with trading the news may have been that short-term traders were something like 92% bearish on the S&P futures and 100% bullish on bonds. Everybody expected the world to fall apart. Traders were 76% bullish on gold. So then the news hit commodities hard but stocks were supported by the lower oil prices and interest rates held up pretty well. Going into this quarter’s release, S&P futures had traders maybe 88% bearish but 100% bearish on bonds and the low 50% bullish on gold. Crappy news again this time weighed on interest rates but everything else seems to be holding up. Now we have S&P weekly slow stochastics trying to roll over and shorter measures doing the same but you have 85% of short-term traders already bearish on stocks. Seasonality is ugly but it’s hard to trade for the likely negative news when everyone is so bearish. Almost the whole decline in gold saw traders bullish at above 70% and it wasn’t until this sentiment suddenly dropped a good 20% before gold bottomed out. Maybe the news will hit stocks a bit and traders will become more bullish after a pullback which might allow for a real move lower to take place but week after week I’ve watched traders be bearish on stocks as they hit new highs and bullish on gold with each new low. Think back to last May when everybody was so bearish on wheat heading into strong seasonality and a 4-year cycle bull market. In gold terms, wheat was priced lower than when oil traded below $11/brl. Sentiment or trader commitments seems so key to the big moves and trading the news.

    http://www.investing.com/indices/us-spx-500-futures

Archives

Resources & Links

Search