Hi everyone!
We have ANOTHER WEBINAR on the schedule for you! Tune in next week – December 18 at 12:00pmET – to hear Galen Moore interview Kyle Samani of Multicoin Capital and Jordan Clifford of Scalar Capital about how funds use crypto lending services, where interest rates are going, sector liquidity and more. You don’t want to miss this one.
And if you missed our last webinar on crypto markets and exchanges, you can hear it here.
You’ll notice below that there are a ton of new products launching in the crypto space. Demand is proving slow to catch up, but the bustling activity shows that next year will most certainly be interesting.
We have a special feature in THE BRIEFING for you today: Jesus Rodriguez, CTO of blockchain analytics firm IntoTheBlock and a renowned AI expert, talks about the difficulties of sentiment analysis in the crypto sector.
With that, buckle up and read on… |
|
Jesus Rodriguez is the CTO and co-founder of IntoTheBlock , a platform focused on enabling an intelligent infrastructure for the crypto markets, as well as chief scientist of Invector Labs and an active investor, speaker and author in the crypto and artificial intelligence markets. The opinions expressed in this article are his, and do not reflect CoinDesk’s position.
Myths and Realities: Sentiment Analysis for Crypto Assets
One of the established beliefs in the cryptocurrency markets is its susceptibility to news and social media. Like any other nascent and still irrational financial market, unexpected developments captured in news or social media tend to impact price. As a result, there is increasing interest in leveraging machine learning techniques such as sentiment analysis to detect possible correlations with the price of cryptocurrencies and digital tokens. Despite its importance, most attempts to leverage sentiment analysis are too basic to output any tangible intelligence and quite often produce misleading results.
The challenges of efficiently leveraging sentiment analysis to evaluate the behavior of an asset are not unique to the crypto space. Producing true insights based on textual sentiment is a very difficult task that, most of the time, requires natural language processing (NLP) models optimized for a specific financial domain. Large quantitative hedge funds use armies of machine learning experts to train NLP models in a very specific task like analyzing earning reports in order to get an edge in a medium frequency trade. Efficiently leveraging sentiment analysis for crypto assets requires machine learning depth and rigor.
To understand that statement, let’s start by diving a bit deeper into the characteristics of sentiment analysis methods.
A Gentle Introduction to Sentiment Analysis
In act II, scene II of the famous play Richelieu; Or the Conspiracy, British playwright Edward Bulwer-Lytton coined a phrase that has transcended generations: “The pen is mightier than the sword.” Centuries after, that famous quote brilliantly encapsulates the importance of sentiment analysis. Emotions in textual communication are sometimes more conducive to actions than physical actions themselves.
Conceptually, sentiment analysis is a subdiscipline of NLP that focuses on identifying the affective states of textual communications. Contrary to popular beliefs, sentiment analysis is not a single technique but rather a subdiscipline of the deep learning space that covers different types of affection detection in textual data. From that perspective, there are several types of sentiment analysis that could be relevant in the context of crypto-asset intelligence: - Polarity Analysis: This type of sentiment analysis ranks textual sentiment in positive, negative and neutral. For instance, the sentence “the bitcoin price rally has reenergized the market” would likely be classified as positive by most models.
- Emotion/Tone Analysis: Instead of an overall qualifier for the text, this type of analysis centers on scoring the different types of emotions present in a particular text. Emotions such as sadness, happiness or anger are a common focus of emotion analysis algorithms. For instance, the sentence “this bitcoin rally is crazy,” will show high levels of excitement and joy.
- Aspect Sentiment Analysis: This type of sentiment analysis focuses on interpreting the sentiment about specific subjects within a sentence rather than a sentence as a whole. For instance, in the sentence “Bakkt futures are a major milestone for the bitcoin market,” aspect analysis will determine the sentiment related to “Bakkt futures” instead of the complete sentence.
Looking at the previous list, we can clearly see the benefits of sentiment analysis for crypto assets. However, there are also plenty of challenges that should be considered before venturing into using these types of techniques. Contextualization, subjectivity, irony or even bad grammar are among the factors that can easily trick the best NLP algorithms.
Sentiment Analysis for Crypto Assets
Crypto is a nascent asset class that is still vulnerable to the irrationality of financial markets and the lack of proper disclosure channels. From that perspective, it is only logical to assume that NLP techniques such as sentiment analysis can identify alpha or smart beta generator factors to predict the behavior of crypto assets. Reality is a bit different.
When applying sentiment analysis to crypto assets, we are likely to encounter two main types of challenges: - Limitations of mainstream NLP technologies when applied to a domain-specific problem such as crypto asset analysis.
- Incorrect assumptions about how sentiment is reflected in news and social media.
The first challenge can almost be seen as an unexpected side effect of the rapid growth of NLP technologies. Today, it is relatively easy for a developer to incorporate sentiment analysis into applications using simple APIs that don’t require any deep learning expertise.
While NLP APIs can be effective analyzing the sentiment of a generic sentence, they perform extremely poorly when trying to extrapolate domain-specific knowledge of a specific sentence. For instance, analyzing the sentence “a bitcoin ETF approval could be imminent” requires NLP models that are specialized in the semantics of market-specific terminology and that are able to extrapolate sentiment at a more granular level than from just a sentence.
The second challenge is related to misconceptions about how sentiment is reflected in news and social media commentary. As a source of intelligence, news can be highly informative but quite useless when comes to sentiment analysis. The reason is obvious: the sentiment in well-written news should trend around neutral. Social media behaves in the exact opposite way. Conversations about cryptocurrencies in Twitter or Telegram tend to contain relevant sentiment but, for the most part, are based on a reaction to public material information, which means that they are unlikely to generate any informational edge. Additionally, social media threads tend to be noisy and relatively subjective, which can produce misleading sentiment analysis results.
From a purely technological standpoint, building effective sentiment analysis models for crypto assets requires models trained in the terminology of crypto markets, but that also analyze news as sources of information and social media feeds as amplifiers of sentiment. However, if we get past this technological challenge, we are now faced with one of the biggest psychological misconceptions when comes to sentiment analysis models in the crypto space.
The Sentiment-Market Impact Fallacy
The sentiment-market impact fallacy describes a phenomenon that is notorious or irrational, such as nascent financial markets in which investors assume a direct correlation between a sentiment score and a price movement. To explain this behavioral economics dynamic, let’s imagine that you are using an analytics tool that analyze the sentiment of recent bitcoin tweets. Psychologically, most investors are inclined to interpret the sentiment as a leading indicator based on the following rules: - If the sentiment is positive that’s a bullish indicator for the price of bitcoin.
- If the sentiment is negative that’s a bearish indicator for the price of bitcoin.
However, if your model is analyzing public, material information, the sentiment should be interpreted as a lagging indicator following some non-intuitive rules: - If the sentiment is positive and the price of bitcoin does not go up, that is a bearish signal.
- If the sentiment is negative and the price of bitcoin does not go down, that is a bullish signal.
Being aware of sentiment-price bias positions sentiment analysis not as a leading indicator but as an often relevant factor in a trading strategy.
From Sentiment Analysis to Market Impact Analysis
From an informational standpoint, the crypto market is noisy and full of unexpected events. In terms of sentiment analysis, that combination of factors is a nightmare. Instead of narrowly focusing on sentiment analysis, we should probably develop a more holistic approach. A sentiment-market impact indicator would be a combination of polarity (negative, positive, neutral), emotion (anxious, excited, sad…) and aspect-based (topics, entities…) analysis over long periods of time. This approach would require the training of models specialized in the dynamics of crypto assets to evaluate the sentiment in the context of specific market conditions.
The idea of sentiment-market impact models is conceptually trivial: quantify the impact that combinations of sentiment, emotions and topics can have on a crypto asset during specific market conditions. Part of the beauty of this approach is that it doesn’t have to be completely unsupervised like most sentiment models today; it can be trained on domain-specific knowledge of crypto markets. For instance, we could train a model to learn that positive articles about Chinese investment in crypto can have a positive impact in a market that had been relatively bearish for the last week. The core principle of sentiment-market impact analysis models would be to contextualize the knowledge of sentiment models to the specifics of the crypto market.
Sentiment analysis is likely to keep sparking flashy headlines in the crypto market. However, in order to be effective, the models require deeper machine learning rigor and the building of knowledge based on the specific dynamics of crypto markets. As the markets evolve, we are likely to see a transition from plain sentiment analysis techniques to more holistic market impact models that quantify the relevance of specific topics in the behavior of the crypto markets.
– Jesus Rodriguez |
* never enough time - I've starred five especially compelling links, but do check out the rest when you can!
BIG IDEAS
*A Look at Innovation in Bitcoin’s Technology Stack (Digital Asset Research) – Bitcoin’s construction may be immutable by design, but in there is a lot of work going on in enhanced functionalities and additional services.
*Four Insights on Crypto Liquidity From Binance US and FTX (CoinDesk) – A recap of the latest CoinDesk Research webinar on market liquidity, with some eye-opening clarifications and a few surprises.
Macro investor Raoul Pal muses on the importance of the development and brain power in the crypto space, and how it is futile to try and put labels on deep innovation.
Deutsche Bank Gives Crypto Enthusiasts Some Hope to Hang On (Bloomberg, paywall) – Rising doubts about the sustainability fiat currencies and a growing concern over privacy could drive more people to digital assets, Deutsche Bank strategist Jim Reid wrote in the firm’s “Imagine 2030” report on 24 alternative ideas for the next 10 years.
State-backed crypto is a contradiction (FT Alphaville) – Apparently the Deutsche Bank report relies on questionable charts and a shaky understanding of what crypto is.
Bitcoin Halving Could Leave Price at $20K-$50K, Hedge Fund Manager Says (CoinDesk) – Assuming demand holds steady, the drop in new supply should provide a price bump, according to professor and fund manager Charles Hwang.
State Street: 38% of Clients Will Put More Money into Digital Assets in 2020 (CoinDesk) – According to a recent survey, 94% of the global custodian’s clients hold crypto assets or derivatives, but none have yet asked it to store them.
Are Miners the Modern Hedgers? (ErisX) – A review of the economic risks crypto miners face.
MARKETS
Delphi Digital’s latest Macro Outlook report (paywall) looks at the recent bitcoin sell-off against a backdrop of a weakening dollar, growing demand for safe haven assets and greater asymmetric risk to the downside for several asset classes.
Bitcoin Volatility Is Up, Liquidity Stagnant (CoinDesk) – Galen Moore shares metrics that show that market maturity has not significantly advanced this year.
*Trading Places: Tron soils Poloniex, Coinbase looks to embrace Wall Street again, and other exchange musings (The Block, paywall) – Frank Chaparro looks at recent changes at Circle, Poloniex, Coinbase and Gemini.
Crypto Funds Are Closing While the Biggest Investors Stand Aside (Bloomberg, paywall) – According to Crypto Fund Research, nearly 70 institution-focused crypto hedge funds have closed so far this year, and the number of fund launches is less than half that of 2018.
*When evaluating spot exchanges based on order book depth, Bitfinex appears the most liquid (The Block, paywall) – A deep look at market liquidity shows that Bitfinex, Coinbase, Kraken, Bitstamp, Binance, and FTX have the deepest liquidity when it comes to BTC, ETH and XRP.
Bitcoin more popular than Netflix stock among millennials; GBTC one of their top 5 equity holdings (The Block) – According to a report published by brokerage giant Charles Schwab, 1.8% of 25-39 year olds hold Grayscale’s Bitcoin Trust investment product, making it the fifth most widely-held investment.
Best-Performing Cryptocurrency Powers Controversial Exchange (Bloomberg, paywall) – Insight into a growing subset of digital assets, and the innovative business models they represent.
A Crypto Trader’s Guide to USDC (Circle) – It’s not just a payment mechanism.
Alex Kruger lifts the lid on the myth that Bakkt’s futures are backed by bitcoin (spoiler: they’re not).
Bitcoin Price Increases During Holidays Again, But Not Because of FOMO (SFOX) – It’s more likely a case of a self-fulfilling prophecy: we expect the price to go up at the end of the year, so it goes up at the end of the year.
LedgerX Places Founders on Administrative Leave After Tussle With CFTC (CoinDesk) – Larry E. Thompson, formerly of the DTCC, has been named as interim CEO and lead director of Ledger Holdings, the derivatives provider’s parent company.
NEW PRODUCTS
Crypto Lender BlockFi Rolls Out Zero-Fee Trading for Bitcoin, Ether, GUSD (CoinDesk) – The firm will enable clients to use deposited assets to buy other assets.
Swiss Startup Amun Wins Regulatory Approval to Sell Crypto-ETPs to EU Retailers (CoinDesk) – The Swedish Financial Supervisory Authority has cleared a base prospectus filed by the ETP manager, which means that EU retail investors with access to the Swiss SIX and German Boerse Stuttgart exchanges can trade various crypto ETPs.
Asset Manager Secures SEC Approval to Create Novel Bitcoin Futures Fund (CoinDesk) – The NYDIG Bitcoin Strategy Fund, a portfolio fund in the Stone Ridge Trust VI, will invest in cash-settled bitcoin futures contracts traded on exchanges registered with the CFTC.
Asia’s Grayscale? Two new bitcoin trust products get launched, with Coinbase as custodian (The Block) – Hong Kong-based asset management firm IDEG Investment has launched two new bitcoin trust products, Asia Bitcoin Trust I and Atlas Mining Trust I, which reportedly have $200 million AUM.
Bakkt Goes Live With Options, Cash-Settled Futures Products (CoinDesk) – Both products settle to the Bakkt Bitcoin (USD) Monthly Futures contract.
Ex-Morgan Stanley Executives Launch Crypto Derivatives Platform in Singapore (CoinDesk) – Phemex claims to be 10x faster than traditional crypto exchanges, and offers perpetual contracts for bitcoin, ethereum and XRP with up to 100 times leverage for retail and institutional investors.
Crypto Exchange OKEx Launching Options Trading Later This Month (CoinDesk) – The Malta-based exchange will commence simulated options trading on Dec. 12, with live trading kicking off on Dec. 27.
BTSE Exchange Plans $50M Token Raise on Blockstream’s Ethereum Rival Liquid (CoinDesk) – The Dubai-based cryptocurrency exchange is looking to sell 50 million tokens at $1 each, tentatively in March 2020.
Ronaldo’s soccer club Juventus now has a token that gives its over 400M fans voting power (The Block) – Juventus now has its own crypto token $JUV, which fans can buy on the Socios platform.
Russia’s Richest Man Starts Testing Sales of Crypto Metal Tokens (Bloomberg, paywall) – MMC Norilsk Nickel PJSC, one of the world’s largest producers of palladium, nickel, platinum and copper, has started testing a platform for digital metal tokens.
Saga Stablecoin Goes Live Backed by Basket of Fiat Currencies (CoinDesk) – The token aims to be a store of value to begin with, morphing into a free-floating asset over time as users buy in and signal their trust in its value.
CRUNCHING NUMBERS
Alex Thorn points out that the number of bitcoin addresses with positive balances has hit an all-time high, but the metric has weaknesses.
An On-Chain Analysis of Litecoin (IntoTheBlock) – 80% of LTC holders would lose money if they decide to sell today, even though the number of long-term holders is steadily increasing.
Security Token Prices, Volumes, & Market Cap Now Live on STOmarket.com (Security Token Group) – Security token sector watchers finally have a dashboard for prices, although for now only six tokens are listed.
REGULATORS AT WORK
Top US Financial Regulators Urge Monitoring of Digital Assets, Stablecoins (CoinDesk) – In the Financial Stability Oversight Council’s annual report, a panel of financial regulators including Treasury Secretary Steven Mnuchin, SEC Chairman Jay Clayton and CFTC Chairman Heath Tarbert recommended that state and federal governments continue to examine the financial risks posed by digital assets.
PODCASTS
*WHAT BITCOIN DID: Peter McCormack has a deep discussion with bitcoin investor and analyst Tuur Demeester about how the emergence of crypto assets has triggered difficult questions which will lead to profound changes in societal structures, financial diversity and business models.
ON THE BRINK: Nic Carter and Matt Walsh chat to Alex Pack, co-founder and general partner at Dragonfly Capital, on the difference between Asian and US crypto ecosystems, the role that regulators play in that, the meaning of “store of value” and the role of tokens in the emerging decentralized economy.
STEPHAN LIVERA PODCAST: Stephan chats with Parker Lewis of Unchained Capital about bitcoin in a macro-economic context.
STATE OF CRYPTO: The Amun team talk about the impact recent regulatory actions could have on token issuances and markets.
A-HA!
Brace for the Digital-Money Wars (Wall Street Journal, paywall) – The financial privacy battle could reach geopolitical levels when countries start issuing their own digital currencies.
What Kind of Capitalism Do We Want? (Project Syndicate) – Klaus Schwab presents the case for “stakeholder capitalism.”
Why is the world's financial plumbing under pressure? (BBC) – The evolution of financial messaging, and how it’s still vulnerable to manipulation.
Why White-Collar Workers Spend All Day at the Office (The Atlantic, paywall) – The digital revolution has given us freedom… to work all hours of the day. |
|
|
|
|
|
FUNDING
Blockchain-based consumer lender Figure Technologies has announced a $103 million Series C raise from Morgan Creek, MUFG, DCG, HCM Capital and others, bringing its valuation to $1.2 billion.
DeFi interface aggregation platform Zerion has secured $2 million in seed funding from Placeholder, Blockchain.com Ventures, and Gnosis.
FIRMS
Student loan and financial services provider SoFi has secured a BitLicense from the NYDFS, which will enable it to provide buy and sell services for a range of cryptocurrencies to New York residents.
HBUS, the U.S. affiliate of the Huobi Group exchange, will cease trading on Dec. 15, allowing customers until the end of January to withdraw their assets. It plans to relaunch in 2020 under a new legal framework.
DXM, the cryptocurrency financial services subsidiary of South Korea’s fintech firm Dunamu, is launching Upbit Safe, an institutional custody service which will use Ledger Vault’s hardware security technology.
Security token platform Securitize has acquired Japan’s blockchain technology consultancy firm BUIDL.
Simplex, which provides fiat gateway infrastructure to several cryptocurrency exchanges including Binance, Huobi and Poloniex, has added support for the Japanese yen (JPY) and the Canadian dollar (CAD).
Clients of crypto order management platform Omniex can now access Seed CX’s institutional digital asset market.
Hive Blockchain Technologies Ltd., the first cryptominer to trade publicly (on Canada’s junior stock exchange), has been dropped by its last remaining analyst.
PEOPLE
Sean Neville, Circle's co-CEO and co-founder, will be stepping down from his role at the end of the month, but will remain on the board as an independent director.
Crypto investor Multicoin Capital has hired Beijing-based investor Mable Jiang, formerly of Nirvana Capital, to spearhead the firm’s expansion into Asia.
Cryptocurrency exchange and custodian Gemini has appointed Julian Sawyer, former COO and co-founder of Starling Bank, as Managing Director overseeing the company’s operations in the United Kingdom and Europe.
Blockchain-based consumer lender Figure Technologies has added Anthony Pompliano, partner at crypto investor Morgan Creek Digital, to its board.
Cryptocurrency financial services firm Unchained Capital has hired Will Cole of the Wyoming Blockchain Task Force as its new chief product officer.
Have a tip? Drop me a line at noelle@coindesk.com. |
|
|
|
|
|
| | Were you forwarded this email? Subscribe here.
Would you like to sponsor this email? Send Jeremy a note.
And please send us feedback - we want to make this newsletter useful for you.
Previous newsletters: 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62
|
CoinDesk is not an investment advisor. This newsletter is for informational purposes only, and any comments here do not constitute investment advice. |
|
|
|
|
|
|