Here’s another Nature news story. I’ll be interested to see what other media outlets make of it.
Traders reveal their mood in the search terms they use.
Suppose you had a direct line into the minds of stock market traders. Would you be able to predict which investment decisions they will take, and thus anticipate the markets?
A team of researchers in the UK and US now suggests that such a crystal ball might exist, in the form of the search terms recorded and made publicly available by Google Trends. Tobias Preis of the University of Warwick Business School and his colleagues say that their analyses of Google Trends data show “early warning signs” of how the markets will shift – including the financial crash of 2008 .
Don’t, however, imagine that this is the way to make a fast buck. It’s one thing to offer a retrospective account of why markets behave as they do – which is what Preis and colleagues have done – and quite another to provide a genuinely predictive tool.
That’s why the work is “interesting but not earth-shattering”, in the view of British economist Paul Ormerod of the consultancy Volterra Partners in London.
Mathematical physicist Didier Sornette of the Swiss Federal Institute of Technology (ETH) in Zürich agrees, pointing out that the predictive power of the strategies the authors deduced from Google Trends data are only slightly better than predictions which assume traders make random decisions. “No investor or hedge-fund would be interested in such a strategy”, he says.
The predictive value of Google Trends has been demonstrated in other areas of social science. Most famously, outbreaks of influenza have been seen emerging in real time by monitoring the numbers of Google searches for terms related to flu prevention and cure .
The potential of using such information to study economic behaviour has already been spotted. Preis and coauthor Gene Stanley of Boston University have themselves shown that certain search terms reflect the volume of stock market transactions . Sornette, in collaboration with Japanese economists, has found that the volatility (fluctuations) of financial markets can be correlated with the prevalence of particular topics in business news .
But what traders and investors really want is a method not just to assess the current state of markets but to anticipate their future course. In particular, episodes of instability, such as the financial crisis of 2008, are often preceded by periods of concern during which investors avidly seek information to decide whether to buy or sell.
Preis and colleagues figured that such anxieties and moods might be signaled by Google search terms. Just before the onset of the latest crisis, for instance, “debt” might be expected to feature prominently. That’s just what the researchers found.
To test if such correlations could be made predictive, they devised trading strategies in which a decision to buy or sell is linked to the recent prevalence of particular search terms. They simulated how these strategies would have performed between 2004 and 2011 based on real data from the financial markets.
Of the 98 ‘Google Trends’ strategies the researchers explored, that based on “debt” performed best. By 2011 it would have increased the value of a portfolio by more than 300 percent, compared with just 16 percent for a common conventional investment strategy.
Although this sounds impressive, the relevance of a predictive Google search term isn’t always clear. The second-best strategy, for example, was linked to “color”, and the fourth best to “restaurant”.
Even the use of “debt” is not obvious, since its role in the financial crash was apparent only as it happened. “How would they know in advance that they should use ‘debt’?” asks Sornette.
“In retrospect it is always possible to derive what appear to be highly successful trading strategies”, says Ormerod. “But what we want is to be able to do that before the event, not after.”
What’s more, economists acknowledge that any transparently profitable strategy for playing the markets will quickly lead to a change of trader behaviour that cancels it – 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”, coauthor Susannah Moat of University College London agrees.
The researchers suggest, however, that a key outcome of their approach might be to elucidate the psychological mechanisms that guide traders to their decisions, which could be encoded in their information-gathering. “Stock market data themselves tell us little about how traders make decisions”, says Preis.
“We think that the overall pattern we observe may reflect loss aversion”, he adds – the fact that humans are more concerned about losing money than they are about missing an opportunity to gain the same amount.
1. Preis, T., Moat, H. S. & Stanley, H. E. Nat. Sci. Rep. 3, 1684 (2013).
2. Ginsberg, J. et al. Nature 457, 1012–1014 (2009).
3. Preis, T., Reith, D. & Stanley, H. E. Phil. Trans. R. Soc. A 368, 5707–5719 (2010).
4. Hisano, R. et al., preprint http://www.arxiv.org/abs/1210.6321 (2012).