Corona Del Mar, CA
Let's answer this freakin' question once and for all...is sentiment data predictive of future prices?
If it's not, then it's just noise and of no use to our goal of making F U money.
I've said for years that sentiment is just someone's opinion...and you know what they say about opinions -- everyone's got one.
|I want to know what they're doing with their actual money.|
But hey, I spent all this money on a supercomputer and machine learning, so let's put this question to bed once and for all.
My team loaded AAII sentiment data into The Boss.
I set up several tests to trade 1) the S&P 500 long/short. 2) S&P 500 long and switch into bonds when not in the S&P 3) Long/cash the S&P 500
The Boss whirled to life, firing up thousands and computer cores to slave away and build me trading strategies from scratch.
Long story short, the sentiment data barely ever got picked for use in a strategy. Price-based strategies easily beat it.
It was like witnessing kids pick players for a dodge ball game, where the weakest kid gets picked last.
For comparison, whenever I add TAP data to a Boss session, it ALWAYS gets picked because it's highly predictive (and you'll never hear a peep about it on CNBC).
So there you have it...another Wall Street sacred cow has been slaughtered.
In the next update, I'll show you what I discovered with index put/call data.
Disclaimer: The results listed herein are based on hypothetical trades. Plainly speaking, these trades were not actually executed. Hypothetical or simulated performance results have certain inherent limitations. Unlike an actual performance record, simulated results do not represent actual trading. Also, since the trades have not actually been executed, the results may have under (or over) compensated for the impact, if any, of certain market factors such as lack of liquidity. You may have done better or worse than the results portrayed.