Citibank: Bitquoin 318,000 (And how to trade it)

Corona Del Mar, CA

Howdy Friend!

Citibank technical analyst recently made a call for "bitquoin 318,000" (I can't spell this correctly because of email censorship).

Now that's a big ballsy prediction that'll get attention (sounds like something a publicist would suggest).

Now I'm not a big fan of drawing lines on charts and making predictions.

In fact, I can't think of a single hedge fund that does that anymore now that machine learning has made it obsolete...

...but it sure did get a lot of attention.

The legendary Paul Tudor Jones is coming around to putting a tiny fraction of his wealth into what I've been calling "nerd currency."

If you've been with me for a few years, you might recall that I did a length video back in December 2017 about why NOT to be bullish on BTC.

It collapsed within a week in brutal fashion -- smashing the dreams of would-be millionaires.

Now that the BTC trust (GBTC) has a market cap of over $10 Billion, let's revisit by feeding BTC price data into "The Boss SuperAi" and seeing what kind of rules it finds.

All I did was add GBTC, added "Score" as the Fitness Function, and then pressed start -- it took less than a minute to set up (Score tries to maximize your annual return, and minimize your drawdowns).

Next, a network of computers in the cloud roared to life and started testing random rules to see what works.

Those strategies with weak performance were killed off and replaced with the offspring of those that had better performance.

Survival of the fittest at work inside a computer network. When I used to do this by hand, it could take me weeks. Now I can automatically discover trading strategies within hours or even minutes in this case.

Houston, we have a problem!

By about generation 7 on most tests I ran, the computer clearly began to over-fit to the past.

I know this because we always leave "out of sample" data to disprove a trading strategy.

That's how science works.

And remember: A trading strategy is just a collection of rules...like a recipe for baking cookies. Combine the ingredients in the right way, and voila! You have a recipe for making money on demand.

The culprit? GBTC has only been trading since 2015. Five years of data on a single symbol is extremely unlikely to work.

It's just not enough time for a strategy to "get to know" a symbol. What works better is decades of data and hundreds of stocks.

However...did I find anything interesting to report as to the characteristics of GBTC?

Yes.

GBTC is clearly momentum driven.

Meaning that it trends much more than reverts to the mean -- which is the opposite of the stock market.

It also seems to be event driven. A single day spike in price can be the catalyst to look for a new trend.

Like a young wine, GBTC is still off limits to me...better to let it age in peace.

But my team has been working on something brand new to the trading world that could quickly change that.

More from me soon!

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.