Five Machine Learning Methods Crypto Traders Should Know About
In a recent article, I discussed the relevance of the machine learning techniques powering the famous OpenAI’s GPT-3 could have for the crypto market. GPT-3 – which can answer questions, perform language analysis and generate text – might be the most famous achievements in recent years of the deep learning space. But, by no means, is it the most applicable to the crypto space. In this article, I would like to discuss some novel areas of deep learning that can have a near immediate impact in the quant models applied to crypto.
Jesus Rodriguez is the CEO of IntoTheBlock, a market intelligence platform for crypto assets. He has held leadership roles at major technology companies and hedge funds. He is an active investor, speaker, author and guest lecturer at Columbia University in New York.
Models such as GPT-3 or Google’s BERT are the result of a massive breakthrough in deep learning known as language pretrained and transformer models. These techniques, arguably, represent the biggest milestone in the last few years of the deep learning industry and their impact hasn’t gone unnoticed in capital markets.
In the last year, there have been active research efforts in quantitative finance exploring how transformer models can be applied to different asset classes. However, the results of these efforts remain sketchy showing that transformers are far from ready to operate in financial datasets and they remain mostly applicable to textual data. But there is no reason to feel bad. While adapting transformers to financial scenarios remains relatively challenging, other new areas of the deep learning space are showing promise when applied in quant models on various asset classes including crypto.
From many angles, crypto seems to be like the perfect asset class for deep learning-based quant models. That’s because of the the digital DNA and the transparency of crypto assets and that the rise of crypto has coincided with a renaissance of machine learning and the emergence of deep learning.
After decades of struggle and a couple of so-called “artificial intelligence(AI) winters,” deep learning has finally become real and somewhat mainstream across different areas of the software industry. Quantitative finance has been one of the fastest adopters of new deep learning technologies and research. It is very common for some of the top quant funds in the market to experiment with the same types of ideas coming out of high tech AI research labs such as Facebook, Google or Microsoft.
Some of the most exciting developments in modern quant financing are not coming from flashy techniques like transformers, but from exciting machine learning breakthroughs that are more developed for quant scenarios. Many of those methods are perfectly applicable to crypto-asset quant techniques and are starting to make inroads in crypto quant models.
Below, I’ve listed five emerging areas of deep learning that are particularly important to crypto quant scenarios. I tried to keep the explanations relatively simple and tailored to crypto scenarios.
Blockchain datasets are a unique source of alpha for quant models in the crypto space. From a structural perspective, blockchain data is intrinsically hierarchical and is represented by a graph with nodes representing addresses connected by edges representing transactions. Imagine a scenario in which a quant model is trying to predict volatility in Bitcoin in a given exchange based on the characteristics of addresses transferring funds into the exchange. That kind of model needs to operate efficiently over hierarchical data. But most machine learning techniques are designed to work with tabular datasets, not graphs.
Graph neural networks (GNNs) are a new deep learning discipline that focuses on models that operate efficiently on graph data structures. GNNs are a relatively new area of deep learning being invented only in 2005. However, GNNs have seen a lot of adoptions from companies like Uber, Google, Microsoft, DeepMind and others.
In our sample scenario, a GNN could use a graph as input representing the flows in and out of exchanges and infer relevant knowledge relevant to its impact on price. In the context of crypto assets, GNNs have the potential of enabling new quant methods based on blockchain datasets.
One of the limitations of machine learning quant models is the lack of large historical datasets. Suppose that you are trying to build a predictive model for the price of ChainLink(LINK) based on its historical trading behavior. While the concept seems appealing it might prove to be challenging as LINK has a little over a year of historical trading data in exchanges like Coinbase. That small dataset will be insufficient for most deep neural networks to generalize any relevant knowledge.
Generative models are a type of deep learning method specialized in generating synthetic data that matches the distribution of a training dataset. In our scenario, imagine that we train a generative model in the distribution of the link orderbook in Coinbase in order to generate new orders that match the distribution of the real orderbook.
Combining the real dataset and the synthetic one, we can build a large enough dataset to train a sophisticated deep learning model. The concept of generative model is not particularly new but has gotten a lot of traction in recent year with the emergence of popular techniques such as generative adversarial neural networks(GANs) which have become one of the most popular methods in areas such as image classification and have been used with relevant success with time series financial datasets.
Labeled datasets are scarce in the crypto space and that severely limits the type of machine learning quant models that can be built in real world scenarios. Imagine that we are trying to build an ML model that makes price predictions based on activity of OTC desks. To train that model, we would need a large labeled dataset with addresses belonging to OTC desks which is the type of dataset that only a few entities in the crypto market possesses.
Semi-supervised learning is a deep learning technique that focuses on the creation of models that can learn with small labeled datasets and a large volume of unlabeled data. Semi-supervised learning is analogous to a teacher presenting a few concepts to a group of students and leaves the other concepts to homework and self-study.
In our sample scenario, imagine that we train a model with a small set of labeled trades from OTC desks and a large set of unlabeled ones. Our semi-supervised learning model will learn key features from the labeled dataset such as trade size or frequency and will use the unlabeled dataset to expand the training.
Feature extraction and selection are a key component of any quant machine learning model and is particularly relevant in problems that are not very well understood such as crypto asset predictions. Imagine that we are trying to build a predictive model for the price of Bitcoin based on order book records.
One of the most important aspects of our effort is to determine which attributes or features can act as predictors. Is it the mid-price, the volume or a hundred other factors? The traditional approach is to rely on subject matter experts to handcraft these features but that can become hard to scale and maintain over time.
Representation learning is an area of dep learning focused on automating the learning of solid representations or features in order to build more effective models. Instead of relying on human feature modeling, representation learning tries to extrapolate features directly from unlabeled datasets. In our example, a representation learning method could analyze the order book and identify hundreds of thousands of potential features that can act as predictors for the Bitcoin prices. That level of scaling and automation is impossible to achieve in manual feature engineering.
The process of creating quant machine learning models remains highly subjective in many aspects. Let’s take the scenario of a model that is trying to forecast the price of Ethereum based on activity in a set of DeFi protocols. Given the nature of the problem, data scientists will have certain preferences about the type of model and architecture to use.
In our scenario, most of those ideas would be based on domain knowledge and subjective opinions about the way the activity in DeFi protocols can impact the price of Ethereum. Given that machine learning is based on building knowledge and knowledge is not a discrete unit, its almost impossible to debate the merits of one method versus another for a given problem.
Neural architecture search(NAS) is one area of deep learning that tries to automate the creation models using machine learning. Sort of using machine learning to create machine learning. Given a target problem and dataset, NAS methods will evaluate hundreds of possible neural network architectures and output the ones with the most promising results.
In our sample scenario, a NAS method can process a dataset that incorporates trades in decentralized exchanges and produce a few models that can potentially predict the price of Ethereum based on those records.
The methods described above represent some emerging and more developed areas of deep learning that are likely to have an impact in the crypto quant models in the short term. And, those are by no stretch the only areas of deep learning crypto quant should pay attention to.
Other deep learning disciplines such as reinforcement learning, self-supervised learning and even transformers are rapidly making inroads in the quant space. Research and experimentation about deep learning techniques applied to quant models is happening everywhere and crypto stands to be a great beneficiary of that wave of innovation.
Crypto Community Respond To BoE Governor On Bitcoin’s Intrinsic Value
The intrinsic value of bitcoin has been discussed heavily in the crypto space for several days now after a remark by the governor of the Bank of England (BoE) suggested that the flagship crypto might have no intrinsic value.
Andrew Bailey, BoE Governor, commented on bitcoin’s intrinsic value in a question and answer session with members of the public early this week. He was quoted by Reuters as saying:
“I have to be honest, it is hard to see that bitcoin has what we tend to call intrinsic value. It may have extrinsic value in the sense that people want it.”
He also said that people who use bitcoin for payments make him quite nervous since the value of cryptocurrency is still uncertain. After those remarks by Bailey, the crypto community started discussing bitcoin’s intrinsic value in some detail.
The CEO of Nasdaq-listed company Microstrategy, Michael Saylor, also had his say in this matter. Microstrategy recently purchased $425 million worth of bitcoin for its treasury reserve. Saylor tweeted:
“Bitcoin is the first digital monetary system capable of storing all the money in the world for every individual, corporation, and government in a fair & equitable manner, without losing any of it. If that’s not intrinsically valuable, what is?”
Nikolaos Panigirtzoglou, JPMorgan’s strategists, wrote in a note on October 13 about bitcoin’s intrinsic value approaching its market price.
“Bitcoin faces a ‘modest headwind’ in the short term based on an analysis of bets in the futures market and an estimate of the cryptocurrency’s intrinsic value.”
Bloomberg reported the strategists explaining and added that they said the price remains almost 13% higher than an estimate of intrinsic value.
Several people on Twitter were quick to point out that bitcoin may have no definite intrinsic value. But, fiat currencies also do not have intrinsic value. The Federal Reserve Bank of St. Louis wrote a report in 2018 saying:
“Bitcoin is not the only currency that has no intrinsic value. State monopoly currencies, such as the U.S. dollar, the euro, and the Swiss franc, have no intrinsic value either. They are fiat currencies created by government decree. The history of state monopoly currencies is a history of wild price swings and failures. This is why decentralized cryptocurrencies are a welcome addition to the existing currency system.”
Shapeshift CEO Erik Voorhees said that there is no such thing as intrinsic value. He explained:
“Value is always subjective, in the eyes of the valuer … Gold, bitcoin, fiat, rice: none have ‘intrinsic value.’”
Another Twitter user, Bob McElrath, also agrees that nothing has intrinsic value since the name ‘value’ is human sentiment. Value changes from time to time and with circumstances. Anybody who tries to convince you otherwise in most cases wants to sell something to you for their gain. McElrath added:
“Despite not having ‘intrinsic’ value, bitcoin has a sophisticated, market-based way to determine its value, not only on the demand side but on the supply side as well. Of course, this statement is true for any commodity.”
George Selgin, Cato’s Center for Monetary and Financial Alternatives director, opined:
“Of course no goods have ‘intrinsic’ value. Some (like any fiat money) also lack ‘non-monetary use value’ … the Bank of England’s observation that bitcoin lacks intrinsic value is an instance of the pot calling the kettle black.”
This debate can go on and on but that does not deter interested investors from diving into the bitcoin space. More institutional investors are joining the market which many proponents believe is a positive sign for the future of bitcoin and cryptos in general.
How Three Crypto Unicorns Going Public In 2021 Could Boost Bitcoin
Something special seems to be brewing in the crypto industry lately. Bitcoin is becoming a respected and mature financial asset, and the businesses associated with them are finally getting the respect they demand too.
The next year, a major catalyst for the next crypto bull market could be a variety of crypto companies going public by way of IPO, bringing much-needed interest and attention from traditional finance into the world of emerging digital assets. Here are the three crypto unicorns one analyst expects to see go public next year, along with one more company that could follow suit – and what the impact this might have on Bitcoin and the greater crypto industry.
Years ago, the crypto bubble that brought Bitcoin to $20,000 and Ethereum to $1,400 and made them household names, had very little to do with the companies that offered these digital assets.
Coinbase, for example, is a financial powerhouse in its own right, offering lending, borrowing, education, and more, right alongside investing. But Coinbase is just one of three giants that crypto analyst and market commentator Ryan Selkis has his “money on” that goes public in 2021.
My money is on three U.S. crypto unicorns going public in 2021, Coinbase, DCG, and BlockFi ($1bn at IPO?)
Of the three, Coinbase may be the most interesting bellweather for public market crypto appetite as it’s the only one that’s likely down from 2018 revenue.
— Ryan Selkis (@twobitidiot) October 14, 2020
He says of the three he expects, Coinbase “may be the most interesting bellwether for public market crypto appetite,” and points out the company’s revenue is down year-over-year since 2018 – when retail FOMO finally fizzled.
Coinbase IPO rumors first appeared earlier this year, and now it has since caused a ripple-effect of other companies that are expected to follow suit.
Selkis also expects blockchain-based wealth management services provider BlockFi and the Barry Silbert-led Digital Currency Group to follow the lead and debut publicly with an IPO.
While Selkis doesn’t mention another crypto project, Ripple was also rumored to be considering an IPO but may have run into a regulatory snafu that is prompting the company to potentially relocate to further its goals as a business.
Could Crypto Unicorns Going Public Help Set A New High In Crypto Market Cap? Source: CryptoCap-Total on TradingView.com
The cryptocurrency total market cap is still down by more than half from its previous all-time high.
While any of the money coming into IPOs won’t contribute to this figure at all, it is more than probable that if crypto takes the limelight in the traditional asset space, cryptocurrencies themselves like Bitcoin and Ethereum will see a major boost, and so will the total crypto market cap.
Featured image from Deposit Photos