Two recent posts included the word “news”, but in different senses.
“News” in the sense of reports on events was discussed in “News analytics”. We can think of this as an approximation to objective reality.
The post “Volatility estimation and time-adjusted returns” used “news” in the sense of “that which moves market prices”. News in the first sense is only part of this sort of news. This sort also includes market participants watching each other.
A surprise (to me at least) was how little effect non-trading days — weekends and holidays — seem to have on the size of returns for the days following them.
It occurs to me that perhaps there is a way of decomposing volatility into exogenous and endogenous components. The exogenous part would be measured by the flow and sentiment from news analytics data, the endogenous would be the remainder.
Almost surely a stupid idea, but there it is.