Embarrassing Confession (Part 3)
Corona Del Mar, CA
Howdy Friend!
Editor's Note: This is part 3...you can read
Part 1 here >>
Part 2 here >>
So let's talk about a unique trading strategy to make money during volatile times...but first, let's talk about another embarrassing confession.
The reason we got started with supercomputing back in 2017 was to test every stock market pattern, and see which make the most money.
Long time readers might remember how I discovered several intraday patterns back in 2008 and made a small fortune.
One subscriber, the founder of one of the largest golf companies, said it was the most consistent gains he'd ever seen.
(Actual results, not theoretical)
Anyhoo...we ended up testing every price pattern in every stock since the 80's.
We analyzed the most profitable patterns from which we could predict the percentage gain of a stock...and only buy the stocks predicted to go up the most (or down the most to short).
Brilliant right?!
Hundreds of thousands of dollars and 12 months later, I can tell you two things:
1) Elliott Wave is pure BS.
2) Price pattern trading on daily bars doesn't work well enough to make it tradeable.
I definitely got egg on my face for this project. Probably 1000 hours of my personal time wasted. My team put in huge amounts of time as well.
I was disappointed as a coyote with a rubber chicken.
They were compensated of course, but no one wants to build a bridge that collapses.
But there was a silver lining...
We pivoted...took what we learned about The Cloud and created The Boss "SuperAi" automated strategy builder.
That has worked extremely well, and we have a lot of happy campers.
But I still haven't been able to get something out of my head...the ability to predict the percent gain a stock will go up or down over the next few days!
Who wouldn't want that?!
Even better, if you buy the top let's say 10 stocks and sell short the bottom 10, you'll have a market neutral strategy.
Renaissance Technology has made about $5 billion a year doing just that, so I know it can be done. Honky tonk 'til you drop if we can get a piece of that pie!
Last week I was feeling sick with a stomach ache, watching re-runs of Lost.
One of the characters was a physicist with an expertise in time travel...he was writing a bunch of equations on a chalkboard like a madman.
I suddenly had visions of computer code in my head and I too began scribbling like mad -- on my notebook. I realized we could insert very primitive code into The Boss "SuperAi" and create predictions.
Over time, we could "breed" computer code together like we already do for trading indicators. Like this:
C# computer code is Turning Complete, which means if there's an answer to solving this problem (predicting percent gains with some degree of accuracy) it'll find it given enough time and computing power.
Turns out that we have plenty of computing power (soon to be 3580 computer cores), so I guess it could be just a matter of time.
What exciting times!
P.S. Want to see a demo of The Boss "SuperAi"? Watch as I create four trading strategies with just a few clicks of the mouse.
If you're looking to speed-fund your retirement with less risk, then this could be for you. Click here now (this is the FINAL week) >>
|
|
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.
Responses