“When the language used by financial analysts and reporters becomes increasingly similar the stock market may be overheated, say scientists.”
“After examining 18,000 online articles published by the Financial Times, The New York Times, and the BBC, computer scientists have discovered that the verbs and nouns used by financial commentators converge in a ‘herd-like’ fashion in the lead up to a stock market bubble. Immediately afterwards, the language disperses.”
"Our study shows that reporters converge on the same language — ‘stocks rose again’, ‘scaled new heights’, or ‘soared’ — as their commentaries became more uniformly positive in the lead up to the 2007 crash."
Interesting. Stocks become increasingly correlated at tops and bottoms, so it’s questionable what added benefit text mining for correlation between words would provide.
Here are a few more notes on correlation:
Short Term : Volatility Correlation
- Going back to late 2002, yesterday’s volatility correlates with today’s volatility by a whopping .75. That means that we can predict more than half of the variance in today’s volatility simply by knowing the prior day’s trading range. If we go out to a five-day period, the correlation between the prior five-day’s average range and today’s range has been .80.
- Source : Traderfeed
Medium Term : Below are a couple other studies that may be of interest :
- 63 day rolling daily return correlations (S&P 500 / Newedge CTA Index) show when correlations between the two indices are above 1 standard deviation, the S&P outperforms over the 10 year period of January 2000 to November 2010
- The annualized return was 13.98% compared to -2.95% when below, and a 0.49% total return for the S&P 500
- Source : Hedge Fund Journal / NewEdge
- Macro : "There is a striking correlation between freer capital mobility and the incidence of banking crises." Ken Rogoff and Carmen Reinhart’s “This Time is Different: A Panoramic View of Eight Centuries of Financial Crises”
- Engle’s new project is a book called "Forecasting Correlation" and one of his current projects involves analyzing volatility to determine whether a country’s macroeconomic fundamentals determine it’s volatility.
Popularity: 1% [?]