Is ETC the canary in the mine?

Well, after a couple of weeks where the models have just held on to all cryptocurrencies we have today our first sale. ETC was sold for USD at a rate of 6.458 after commissions; a gain of 140% from the purchase price of 2.69.

This is probably a good intro into discussing a few questions we’ve been fielding from  our backers of late – first, and most important, are these results realistic?  Well if the question is are these results real? then the answer is yes – we will be publishing the brokerage statements from Bitstamp and Poloniex shortly which is where all the trades have been executed to date. Is the performance what we expect over the time period – absolutely not. In many ways it would have been better if we had started our live funds trial at a more “normal” period as showing a 59% gain over a 6 week period without leverage is a complete outlier. We wait with anticipation to see how much of this profit the model keeps when we get a market setback.

Still, in terms of model behaviour, we are encouraged by the way the AI model has performed – even in a flat out bull run there is always the risk that the models would have tried to pick a top too early – instead they have held their positions seeing some spectacular gains over the 6 week period. The real stand-out now is Ripple, the last market for the model to buy. We are now seeing an astounding 448% gain on this market – remarkable even by cryptocurrency standards.

The other question is are we taking excessive risk? As discussed in the intro we are using zero leverage on these trades. That’s not to say we’re running a conservative portfolio – cryptocurrencies by their very nature exhibit extreme volatility but our strategy does not aim to increase that volatility any further.

The third question is selection of cryptocurrencies. Well we did do some pre-screening to ensure there was a relatively liquid market in each of the coins we allow the models to trade. We also wanted to ensure that the coins were tradable on at least 2 of the leading exchanges that we selected to trade on. Finally, we weighted the initial investment by the market capitalisation of the various coins we allow the models to trade in. This is a one off balancing of the capital; moving forward profits made by trading a particular coin will be re-invested in trading that same coin. This should see the portfolio change composition to a larger percentage being held in the more volatile currencies (providing that the trading is profitable).

So with those caveats and explanations what are the scores on the doors after liquidating our ETC position.

We are now showing a gain of 59.09% on the overall portfolio; our comparison strategy (buying and holding BTC) is showing a gain of 52.73% so we are now outperforming the naïve buy and hold strategy by 6.36%, even in a raging bull market. Best performer, as mentioned earlier, is Ripple, showing a gain of +458%, worst performer is Monero showing a gain of “just” 28.3%. Full results below.

CurrencyStarting BalanceUSDCryptoRateUSD EquivTOTALGain/loss
Ether Classic$203.00$487.3906.55$0.00$487.39140.09%
Hold BTC$16,900.00$0.0016.172248801596$25,810.91$25,810.9152.73%

— Wintermute —



Comparison to Buy and Hold …

A few days back one of our readers suggested that a useful comparison would be to compare the performance of our AI models to the performance of just holding Bitcoin (Thanks for the idea Slayer). The suggestion, quite rightly, was that with cryptocurrencies on a roar a user could get good gains just from sitting in Bitcoin so it would be good to see the added value from the models. I liked the suggestion immediately because, as was suggested by the poster, it provides a comparison against simply buying and holding Bitcoin in it’s own right – largely seen as the Gold Standard for Cryptocurrencies.

It also allows us to split our performance into Beta (how well we track the return on the designated market) and Alpha (how well we outperform the return on the designated market). So before publishing the regular results plus the bitcoin comparison I should clarify what this is and what this isn’t.

First what it is. We have taken the bitcoin price at start of the experiment (our first post) and assumed that the comparison is to fully invest in Bitcoin at that point in time. We then hold onto the bitcoins for the full duration of the experiment. This model incurs no commission (we assumed zero commission on the initial trade). This forms the basis of our comparison.

Now what it isn’t. This is not a comparison of how the models would have done if trading against bitcoin (flattening back into bitcoin rather than USD). To do that would require a retraining of the model as the relative strengths and relationships would be very different.

So with that said, current overall performance has continued to be way over long term expectations, we are now showing a gain of 54.61% since inception which is far from expected returns.

CurrencyStarting BalanceUSDCryptoRateUSD EquivTOTALGain/loss
Ether Classic$203.00$0.0075.471698117.3$550.94$550.94171.40%
Bitcoin Hold$23,938.00$0.0022.907177031573$36,032.99$36,032.9950.53%

As can be seen buying and holding also returned exceptional performance, 50.53%, giving us a modest outperformance of 4.08% in little over a month. The closeness of the two models shouldn’t be any surprise as it has been a period where the models have been long for much of the month. The other factor which results in similar performance, at least at first, is the fact that 70% of our starting funds were committed into bitcoin. In fact, the surprising thing is that we have been able to outperform at all. The real test of the value of the models will come when we eventually get a downturn and, although it feels like this will never happen at the moment, it will and we should watch the relative performances as the model actually needs to start actively trading the markets.

Thanks for reading,


— Wintermute —