Can Lexicon predict unemployment trends?
Haven’t dug too deep into this dataset but I thought these were interesting. Looks like Lexicon begins to “overshoot” in late January…perhaps because the phrase “laid off” refers not only to new layoffs, but also layoffs that happened in the previous months.
I’m sure some hedge fund can use this data to make some quick chalupes before the weekly Bureau of Labor Statistics announcements. As these highly predictive real-time signals from Facebook, Google, Twitter, etc. become better instrumented and trusted, the slower government and corporate statistics become far less important…and markets can avoid the sort of volatility that comes after unemployment and earnings announcements.
