Under The Hood - May 2021 - Crypto Autopilot

What a month! Everything was smooth sailing and then suddenly turned around on May 12. Bitcoin had its worst month in 10 years (-36.13%) and the past 2 weeks were so tumultuous that we even felt compelled to send you a reminder to carefully ponder your next steps.

With the month now concluded, let’s recap what happened in Crypto and the Crypto Autopilot; so you can ponder further.

💨 TL;DR

  • This May we kept outgrowing Bitcoin, but outgrowing Euros proved complicated. The ₿ - denominated performance for the month was 4.52%; the €-denominated performance was -33.67%.

  • As May came to an end, the Crypto Autopilot held: SOL: 20.1%; BTC: 17.5%; ADA: 9.4%; DCR: 7.5%; MKR: 7.5%; TFUEL: 7.4%; WAVES: 5.4%; MANA: 4.9%; VET: 4.4%; MATIC: 3.8%; KSM: 2.9%; LUNA: 2.5%; CAKE: 2.3%; EGLD: 1.4%; FIL: 1.2%; HBAR: 1.1%

  • NEAR, SiaCoin, Bancor, ThorChain, Reserve Rights, ThetaFuel, NANO, and IOST were all added to the universe, and BAND was removed.

  • In the Q&A section, we explain which tokens have been driving portfolio performance since January, how the Crypto Autopilot learns, and why we don’t have stablecoins in the universe to retreat in times of troubles (but we do have OSOM DeFi Earn for your fixed-income needs).

  • Despite heavy volatility, and Bitcoin’s worst month in about 10 years, from a “builder and long term investor” point of view, the month was pretty good. Except on BSC where protocols got hacked left and right.

🎢 May was a rollercoaster ride, it started well and then about € 369B were wiped off the total Crypto Market Cap.

(1) Following the trend reversal on May 12, the Total Market Capitalization of Crypto is back to where it was around March 24, at about €1.3T. That’s a 23.01% drop. And with a 33.67% drop, Bitcoin’s worst month in 10 years.

It seemed to have arisen from a multitude of factors that coalesced into a perfect self-reinforcing storm :

  1. Elon Musk started a wave of doubt by saying Tesla would no longer accept Bitcoin as payments, and that Dogecoin was better, which prompted a slew of Media attention.
  2. This in turn incited the Media to pay closer attention to all things crypto and to pick up the “news” that China was reiterating (because it had been that way for years) its caution towards cryptos and trying to ban Bitcoin Mining. But they framed it as “news”, which further fed the F.U.D. (Fear, Uncertainty, and Doubt), and the selling.
  3. And since a lot of traders were trading with borrowed money, the falling prices resulted in a lot of them getting “liquidated” (it means that their collateral was sold to pay off their debt), which reinforced the downward pressure on price as all of their crypto collateral ended up on offer on the market.

Interestingly, this seems to be more driven by crowd psychology (reinforced by liquidations) than driven by any change in the fundamentals. Builders keep building and the ecosystem keeps improving. We are really seeing no reason to back away from the space anytime soon. If anything, we are doubling down 😎.

(2)This month again, the total market cap of crypto excluding Bitcoin did better. It only fell by 14.4%. Some of that is because Polygon (MATIC), Cardano (ADA), Celsius (CEL), and a slew of pretty small coins helped to mitigate the losses.

But there was also quite a bit of stablecoin growth this month - for example, Tether's market cap grew by 20% - which inflates the Total Market Cap of Crypto while it’s just dollars or euros or yen being brought on-chain, not innovation being valued. If we look at an alternative benchmark, the CMC Crypto 200 Index ex-Bitcoin (INDEXNASDAQ: CMC200EX) which contains no stablecoins, the performance was -23.09%, so closer to the fall that the Total Market Cap experienced.

(3) Autopilot

The ₿ - denominated performance for the month was 4.52%; meaning that our diversification strategy beat holding Bitcoin alone for the month. When it comes to the €-denominated performance, it was -33.67%.

Since we started, on 26 September 2019, that’s a 673.47% performance in Euros, 91.56% in BTC
Since we started, on 26 September 2019, that’s a 673.47% performance in Euros, 91.56% in BTC

You can check out “Time in the Autopilot And Returns” if you need a reminder of why time in the market is better than timing the market if your day-job isn’t at a Hedge Fund.

If you’ve only recently joined us, we understand the pains of watching a freefall, but simply put, crypto is volatile. We have always recommended a long-term strategy and a long-term view, which are key if you want to reduce risks. So do not be discouraged! We expect to see gains similar to last month’s in the future.

✍️Interesting Crypto Autopilot Moves in May?

We said last month that we thought that the Altcoin season would see more tokens qualify. Looks like we were right!

Dfinity’s ICP token was launched in May and immediately made it to the “TOP 10” after its Coinbase listing. We immediately liked it too and added it to the Universe, but it is not investable yet, because it doesn’t have enough of a track record.

On May 12 - before we noticed any trend reversal and only because of the altcoin season, we moved the constraint of the size of a maximum holding back to 30%, from the 40% where it had been for months. The Autopilot had already moved to hold around 21.7% of Bitcoin at the time anyways and Solana (SOL) was the second-biggest holding at 21.6%.

Solana became the largest holding with (22.8%) on May 13; it became the first time in the Crypto Autopilot’s 595 days of operations that BTC was not the largest position in the portfolio.

Mid-May also saw a lot of new Crypto qualify for inclusion in the investable universe: NEAR, SiaCoin, Bancor, ThorChain, Reserve Rights, ThetaFuel, NANO, and IOST were all whitelisted. But BAND had to be removed as it did not meet the liquidity and market cap requirements anymore.

That brings the total of coins in the investable universe to 62 coins (those are the ones the algorithm can choose from), in a list of 102 projects we think would be worthy (but some of which don’t meet liquidity and market cap requirements)** and the total number of assets which we track to 218**.

🙋 Your Questions on the Autopilot, Answered!

We say it every month, we love getting your questions. So keep them coming, and find all the past answers in the “monthly update” section of this blog.

(1) What are the coins driving the performance?

We went back to the beginning of the year to give you a view of what has been driving the Bitcoin-denominated performance since the start of the year, month-by-month and in total.

Overall, most coins contributed positively to the performance except for AVAX, SUSHI, XLM, NEO, DGB, and ZIL. BNB, THETA, and DCR contributed the most.

(2) What are the holdings in the Autopilot Exactly?

As June started, the Autopilot was holding those 16 coins, in the addressable universe of 62.

SOL: 20.1%; BTC: 17.5%; ADA: 9.4%; DCR: 7.5%; MKR: 7.5%; TFUEL: 7.4%; WAVES: 5.4%; MANA: 4.9%; VET: 4.4%; MATIC: 3.8%; KSM: 2.9%; LUNA: 2.5%; CAKE: 2.3%; EGLD: 1.4%; FIL: 1.2%; HBAR: 1.1%

(3) Is the algorithm learning?

Yes, in some parts, but no on other parts. And it’s not all about the algorithm! So let’s break it down:

To start, you might know the saying “garbage in, garbage out”. That’s because as with most models, it’s only as good as the data you give it and, in this case, the coins it can choose from. That’s why our team reviews coins daily to see whether or not they are good enough to make it into the investable universe. We also impose the constraints (such as the maximum and minimum it can hold in any one coin). Our team is made of real people, and they learn.

Next is the “algorithm”. The portfolio construction Artificial Intelligence (A.I). We say it’s “Artificial Intelligence” because it’s made up of two subfields of AI. : Machine Learning (ML) and Operations Research (OR). OR-based techniques have demonstrated the ability to identify optimal and locally optimal solutions for well-defined problem spaces, and the ML part is ideal for learning with constraints. So it’s good at learning from the ever-increasing amount of data that it gets, but it benefits from the OR-side for portfolio construction, which is all about finding an “optimal” portfolio.

Then there is the aspect of translating all that into actions: how to trade, when, how much, where,... To make sure that the portfolio we’re holding is identical to the optimal one. And that is also up to the team, not the A.I. And careless execution would result in a worse portfolio than the optimal one recommended by the A.I., so we need to do a good job there too.

In conclusion: it learns some, but it isn’t alone. We learn too.

(4) Why don’t you have stablecoins in the universe so that the Autopilot can “retreat” when the market takes a dive like it did this month?

Indeed, we have no stablecoins, no fiat, no gold or commodities (which you can easily find tokenized), or anything other than true crypto projects in the investable universe. The point here is that you can get exposed to the best of what crypto has to offer, but nothing else. And all positions are long so there are no shorts, no derivatives, no options, or anything else. Just plain crypto.

The reason is twofold:

1/ The algorithm seeks "a monotonic growth" which is done by minimizing length and depth of drawdowns and diversifying aggressively (which is the reason why it rarely holds ETH for example because ETH and BTC move in tango, but BTC has less downward volatility, so it sees it as better to satisfy the goals). Also, it invests for the long term whenever it makes a decision (2.5 to 5 years).

So, knowing this and taking into account the volatile nature of crypto, and we saw this in all our backtests, the result is that if you give it cash, it pretty much (not always, but still) takes the largest position in cash that it can. It’s important to remember that there is no “momentum” built into this algorithm. It builds portfolios but doesn't trade (scalping, intraday or swing).

So it would not "try to retreat" very much to cash when seeing the market going down because it’s looking at the long term and long term the market is going up. With a great deal of volatility, but up nonetheless. So yes, if the market is down it follows. And when it's up it follows.

We chose this route because we think that time in the market is more important than timing the market. Morningstar proves this about once a year in their “active/passive” barometer. It’s also the reason why you can find a lot of literature about why investors have lower returns than investments, regardless of the asset class.

2/ Understanding the above, we assume holding cash is not that complicated and most investors have some already. The more cash we would have, the least you would be invested in crypto. So build a portfolio that suits you with a crypto allocation that matches your appetite, but if you want to hold some cash, hold it on the side.

The follow-up question is often: “so you are like an index?”

Not exactly, but not completely different either 😀 We are like an index in the sense that we have a lot of coins potentially investable. But we are different because we don’t rely on market capitalization to decide the weights that each coin gets, and we never hold all of them at once. And that comes with some advantages, because the Index Crypto 200 by Solactive grew 427.47% since 26 September 2019, but the OSOM Crypto Autopilot grew by 673.47%. That’s 250% more.

We think that because crypto is an asset class more like high-growth software startups than established companies, it makes more sense to build a portfolio intelligently than just to go by market cap weights in an index. If you disagree, we’d love to hear you out, let us know by answering this email.

📅 Crypto News & Happenings in May - Month in Review

(1) Speaking on why it’s better to build a portfolio with an A.I. than merely just going with an Index, we had an opinion piece published about that in Nasdaq this week.

(2) Bitcoin had its worst month in 10 years, and everyone is talking about it: CNN, Cointelegraph, Fortune,... That was pretty much News #1 this month. Along with the “crypto CO2 emissions” fears that started it all. But we are a little hesitant to call that “news”.

One thing that is a little worrying is how much protocols on BSC are getting hacked.

(3) Circle is offering companies something like OSOM DeFi earn (only more risky because it is a lot more concentrated). If you also have a company and want an OSOM DeFi Earn account, just reach out to us at [email protected] It’s not a standard process yet, but we are working on it and you could be one of the first!

(4) The former head of the Chinese digital currency initiative said the Yuan CBDC could operate on Ethereum. Wild idea. Imagine the fees you would collect by staking 🤩

So crypto keeps on advancing on its journey to becoming mainstream, big time. Volatility is normal for early-stage startups, it’s just that they aren’t usually publicly traded at that time.

🌼 What Does June Have in Store for us?

(1) As of today already, you can read that this is the end of crypto or that it was just a normal glitch in the bull run. We think none of it matters if you are in it for the long term and think it is worth owning a part of Web 3 before it goes mainstream.

(2)Because if you look at the calendar of upcoming activity for the month, those who announce the death of crypto probably haven’t done a lot of research.

(3) We’ll be launching OSOM DeFi Earn to the world, both on the Web (where it is currently available to all current users at app.osom.finance) and the native Android and iOS apps.

Although we cannot predict what the Crypto Autopilot will choose or what the markets will do in the future, we are concluding May with a model basket that is well-diversified and holding a good BTC position as well.

That’s all for this month. But remember, if June has you looking for a unique gift to celebrate someone you love, 🎁 you can gift Bitcoin or an Autopilot balance very easily.

Feel free to let us know if you have any questions, ideas for how we can improve at [email protected]!


This is not investment advice, nor a solicitation. Crypto markets possess a high level of risk, including volatility and regulatory uncertainty. Past performance does not constitute a guarantee of future results in any way. You are solely responsible for doing your own financial, legal, tax, or investment research before taking any actions.