With the proliferation of blockchain projects and applications, cryptocurrency exchanges, which provides exchange services among different types of cryptocurrencies, become pivotal platforms that allow customers to trade digital assets on different blockchains. Because of the anonymity and trustlessness nature of cryptocurrency, one major challenge of crypto-exchanges is asset safety, and all-time amount hacked from crypto-exchanges until 2018 is over $1.5 billion even with carefully maintained secure trading systems. The most critical vulnerability of crypto-exchanges is from the so-called hot wallet, which is used to store a certain portion of the total asset of an exchange and programmatically sign transactions when a withdraw happens. Whenever hackers managed to gain control over the computing infrastructure of the exchange, they usually immediately obtain all the assets in the hot wallet. It is important to develop network security mechanisms. However, the fact is that there is no guarantee that the system can defend all attacks. Thus, accurately controlling the available assets in the hot wallets becomes the key to minimize the risk of running an exchange. However, determining such optimal threshold remains a challenging task because of the complicated dynamics inside exchanges. In this paper, we propose Shoreline, a deep learning-based threshold estimation framework that estimates the optimal threshold of hot wallets from historical wallet activities and dynamic trading networks. We conduct extensive empirical studies on the real trading data from a trading platform and demonstrate the effectiveness of the proposed approach.
HansâPeter Burghof, Achim Fecker, Patrick Jaquart, Benedikt Notheisen
The 5th European Retail Investment Conference was hosted at Börse Stuttgart, Germany, from April 10th to 12th 2019. The conference chairs invited academics and practitioners to participate and discuss empirical and theoretical research focusing on retail investor products and services, the impact of technology on retail investors, investorsâ decision-making, investor protection schemes, and market microstructure. Albert Menkveld, Professor of Finance at Vrije Universiteit Amsterdam and Fellow at the Tinbergen Institute, held the keynote about the fundamental value of bitcoin.
This paper aims at identifying a validated risk model for the cryptocurrency market. We propose a stochastic volatility model with co-jumps in return and volatility (SVCJ) to highlight the role of jumps in returns and volatility in affecting Value-at-Risk (VaR) and Expected Shortfall (ES) in cryptocurrency market. Validation results based on backtesting show that SVCJ model is superior in terms of statistical accuracy of VaR and ES estimates, compared to alternative models such as TGARCH (Threshold GARCH) volatility and RiskMetrics models. The results imply that for the cryptocurrency market, the best performing model is a stochastic process that accounts for both jumps in returns and volatility.
This study explores the portfolio management of cryptocurrencies by assessing the out-of-sample performance of selected portfolio strategies in the literature. Using daily data from 500 randomly selected cryptocurrencies with monthly and weekly revision, the scaled and stable mean-variance-entropic (MVE) value-at-risk portfolios outperform other portfolio strategies closely followed by 1/N portfolios. The mean Sharpe ratio with transaction costs of both MVE and 1/N was higher than that of benchmark, Coinbase index. Indeed, diversification across cryptocurrencies does improve investment results and mitigates risk exposure. The findings of this research are crucial for practitioners as they showcase a coherent manner to aid fund managers and investors in their investment practices.
Abstract In recent years, the tendency of the number of financial institutions to include cryptocurrencies in their portfolios has accelerated. Cryptocurrencies are the first pure digital assets to be included by asset managers. Although they have some commonalities with more traditional assets, they have their own separate nature and their behaviour as an asset is still in the process of being understood. It is therefore important to summarise existing research papers and results on cryptocurrency trading, including available trading platforms, trading signals, trading strategy research and risk management. This paper provides a comprehensive survey of cryptocurrency trading research, by covering 146 research papers on various aspects of cryptocurrency trading ( e . g ., cryptocurrency trading systems, bubble and extreme condition, prediction of volatility and return, crypto-assets portfolio construction and crypto-assets, technical trading and others). This paper also analyses datasets, research trends and distribution among research objects (contents/properties) and technologies, concluding with some promising opportunities that remain open in cryptocurrency trading.
This letter expands the studies of the informational efficiency in the cryptocurrency market. Most studies have focused on Bitcoin, the foremost known cryptocurrency, and a few more coins. However, this market is more diverse, with cryptocurrencies entering and leaving the market on a weekly basis. This letter fills an important gap in the literature, by studying the informational efficiency using a multi-scaling methodology, which represents a new approach. We compute the generalized Hurst exponent of eighty-four cryptoassets daily returns. The multi-scaling methodology used in this paper find compelling evidence that cryptocurrencies have different degree of long range dependence, and --more importantly -- follow different stochastic processes. Some of them follow traditional monofractal models consistent with fractional Brownian motion, while others exhibit complex multifractal dynamics.
This study measures the volatility of cryptocurrency by utilizing the symmetric (GARCH 1, 1) and asymmetric (EGARCH, TGARCH, PGARCH) model of GARCH family using a daily database designated in different digital monetary standards. The results for an explicit set of currencies for entire period provide evidence of volatile nature of cryptocurrency and in most of the cases, the PGARCH is a better-fitted model with studentâs t distribution. The findings show positive shocks heavily affected conditional volatility as a contrast with negative stuns. Those additional analyses can be provided further support their findings and worthwhile information for economic thespians who are engrossed in adding cryptocurrency to their equity portfolios or are snooping about the capabilities of cryptocurrency as a financial asset.
This paper studies simple moving average trading strategies employing daily price data on the ten most-traded cryptocurrencies that exhibit the âprivacy functionâ. Investigating the 2016â2018 period, our results indicate a variable moving average strategy is successful only when applied to Dash generating returns of 14.6%â18.25% p.a. in excess of the simple buy-and-hold benchmark strategy. However, when applying our technical trading rules to the entire set of ten privacy coins shows that, on an aggregate level, simple technical trading rules do not generate positive returns in excess of a buy-and-hold strategy.
Irfah Najihah Basir, Shaliza Alwi, Masrina Nadia Mohd Salleh, M. Aslam · 5 authors
The concept of cryptocurrency, as part of the digital currency phenomena has been around since 1998 but world-wide adoption only started after the birth of Bitcoin. Financial technology or Fintech is a term used to describe the technological innovation in the financial sector; has seen various major breakthroughs over the past decade, and Bitcoin was right at the center stage. Clearly, a lack of public trust on financial systems after the global financial crisis which describes to the financial crisis of 2007-2008 which started from the subprime mortgage market in the U.S has given cryptocurrency an opportunity to enter the market. Since then, the industry has been growing at a rapid pace driven by increasing acceptance, greater media coverage, sustained inflows, initial coin offering 3 (ICO) frenzy and increased transaction capacity. This study aims to fill the gap by providing insight into the world of cryptocurrency from a Chinese investment perspective. The findings will help the global audience (not limited to those with domicile in China) understand the implication of cryptocurrency as an alternative investment in China. Therefore, this study strives to contribute to the literature and open up a gateway for more future research on FinTech in China.
This project takes several common strategies for algorithmic stock trading and tests them on the cryptocurrency market. The three strategies used are moving average crossover, mean reversion, and pairs trading. Data was collected every five minutes for the top one hundred cryptocurrencies between October 5, 2017, and January 24, 2018. Due to the high volatility of the market, the data includes various market situations. Three noted situations are a rising market, falling market, and relatively stable market. The three strategies were modified to optimally follow each market situation. Modifications include adjusting parameters used in each strategy as well as mixing several strategies or dynamically changing between strategies. In each strategy and with each cryptocurrency, the benchmark against which the algorithm is tested is the market's performance, or what an investor would have after buying and holding. Returns are compared with the buying and holding strategy, and different scenarios are analyzed to determine the risk associated with buying and holding compared with an algorithmic strategy. Results will be taken with the market's actual trends and also with some alternate possible trends to test all market scenarios. A web interface will accompany the presentation, allowing users to test the strategies by entering their own parameters and instantly see the results.
Stephen Dipple, Abhishek Choudhary, James Flamino, BolesĆaw K. SzymaĆski · 5 authors
Abstract The growing interconnectivity of socio-economic systems requires one to treat multiple relevant social and economic variables simultaneously as parts of a strongly interacting complex system. Here, we analyze and exploit correlations between the price fluctuations of selected cryptocurrencies and social media activities, and develop a predictive framework using noise-correlated stochastic differential equations. We employ the standard Geometric Brownian Motion to model cryptocurrency rates, while for social media activities and trading volume of cryptocurrencies we use the Geometric Ornstein-Uhlenbeck process. In our model, correlations between the different stochastic variables are introduced through the noise in the respective stochastic differential equation. Using a Maximum Likelihood Estimation on historical data of the corresponding cryptocurrencies and social media activities we estimate parameters, and using the observed correlations, forecast selected time series. We successfully analyze and predict cryptocurrency related social media and the cryptocurrency market itself with a reasonable degree of accuracy. In particular, we show that our method has impressive accuracy in predicting whether a cryptocurrency market will increase or decrease a day in the future, a significant result with regards to investing and trading cryptocurrencies.
Algorithmic trading is well studied in traditional financial markets. However, it has received less attention in centralized cryptocurrency exchanges. The Commodity Futures Trading Commission (CFTC) attributed the $2010$ flash crash, one of the most turbulent periods in the history of financial markets that saw the Dow Jones Industrial Average lose $9\%$ of its value within minutes, to automated order "spoofing" algorithms. In this paper, we build a set of methodologies to characterize and empirically measure different algorithmic trading strategies in Binance, a large centralized cryptocurrency exchange, using a complete data set of historical trades. We find that a sub-strategy of triangular arbitrage is widespread, where bots convert between two coins through an intermediary coin, and obtain a favorable exchange rate compared to the direct one. We measure the profitability of this strategy, characterize its risks, and outline two strategies that algorithmic trading bots use to mitigate their losses. We find that this strategy yields an exchange ratio that is $0.144\%$, or $14.4$ basis points (bps) better than the direct exchange ratio. $2.71\%$ of all trades on Binance are attributable to this strategy.
We investigate the behaviour of cryptocurrencies using data for bitcoin, ethereum and ripple which account for over 70% of the cryptocurrency market. We demonstrate that $α$-stable distribution is an appropriately sufficient model for highly speculative cryptocurrencies which outperforms other heavy tailed distributions that are used in financial econometrics. We find that the maximum likelihood method proposed by DuMouchel (1971) produces estimates that fit the cryptocurrency return data much better than the quantile based approach of McCulloch (1986) and sample characteristic method by Koutrouvelis (1980). The empirical results show that the leptokurtic feature presented in cryptocurrency return data can be captured by an $α$-stable distribution. The findings highlight that $α$-stable distribution is not only parsimonious with its four free parameters but also a creative model that is close to reality. This paper covers early reports and literature on cryptocurrencies and stable distributions.
Cryptocurrencies, such as Bitcoin, are becoming increasingly popular, having\nbeen widely used as an exchange medium in areas such as financial transaction\nand asset transfer verification. However, there has been a lack of solutions\nthat can support real-time price prediction to cope with high currency\nvolatility, handle massive heterogeneous data volumes, including social media\nsentiments, while supporting fault tolerance and persistence in real time, and\nprovide real-time adaptation of learning algorithms to cope with new price and\nsentiment data. In this paper we introduce KryptoOracle, a novel real-time and\nadaptive cryptocurrency price prediction platform based on Twitter sentiments.\nThe integrative and modular platform is based on (i) a Spark-based architecture\nwhich handles the large volume of incoming data in a persistent and fault\ntolerant way; (ii) an approach that supports sentiment analysis which can\nrespond to large amounts of natural language processing queries in real time;\nand (iii) a predictive method grounded on online learning in which a model\nadapts its weights to cope with new prices and sentiments. Besides providing an\narchitectural design, the paper also describes the KryptoOracle platform\nimplementation and experimental evaluation. Overall, the proposed platform can\nhelp accelerate decision-making, uncover new opportunities and provide more\ntimely insights based on the available and ever-larger financial data volume\nand variety.\n
Cryptocurrencies that are based on Proof-of-Work (PoW) often rely on special purpose hardware to perform so-called mining operations that secure the system, with miners receiving freshly minted tokens as a reward for their work. A notable example of such a cryptocurrency is Bitcoin, which is primarily mined using application specific integrated circuit (ASIC) based machines. Due to the supposed profitability of cryptocurrency mining, such hardware has been in great demand in recent years, in-spite of high associated costs like electricity. In this work, we show that because mining rewards are given in the mined cryptocurrency, while expenses are usually paid in some fiat currency such as the United States Dollar (USD), cryptocurrency mining is in fact a bundle of financial options. When exercised, each option converts electricity to tokens. We provide a method of pricing mining hardware based on this insight, and prove that any other price creates arbitrage. Our method shows that contrary to the popular belief that mining hardware is worth less if the cryptocurrency is highly volatile, the opposite effect is true: volatility increases value. Thus, if a coin's volatility decreases, some miners may leave, affecting security. We compare the prices produced by our method to prices obtained from popular tools currently used by miners and show that the latter only consider the expected returns from mining, while neglecting to account for the inherent risk in mining, which is due to the high exchange-rate volatility of cryptocurrencies. Finally, we show that the returns made from mining can be imitated by trading in bonds and coins, and create such imitating investment portfolios. Historically, realized revenues of these portfolios have outperformed mining, showing that indeed hardware is mispriced.
Yunan Ye, Hengzhi Pei, Boxin Wang, PinâYu Chen · 7 authors
Portfolio management (PM) is a fundamental financial planning task that aims to achieve investment goals such as maximal profits or minimal risks. Its decision process involves continuous derivation of valuable information from various data sources and sequential decision optimization, which is a prospective research direction for reinforcement learning (RL). In this paper, we propose SARL, a novel State-Augmented RL framework for PM. Our framework aims to address two unique challenges in financial PM: (1) data heterogeneity -- the collected information for each asset is usually diverse, noisy and imbalanced (e.g., news articles); and (2) environment uncertainty -- the financial market is versatile and non-stationary. To incorporate heterogeneous data and enhance robustness against environment uncertainty, our SARL augments the asset information with their price movement prediction as additional states, where the prediction can be solely based on financial data (e.g., asset prices) or derived from alternative sources such as news. Experiments on two real-world datasets, (i) Bitcoin market and (ii) HighTech stock market with 7-year Reuters news articles, validate the effectiveness of SARL over existing PM approaches, both in terms of accumulated profits and risk-adjusted profits. Moreover, extensive simulations are conducted to demonstrate the importance of our proposed state augmentation, providing new insights and boosting performance significantly over standard RL-based PM method and other baselines.
The cryptocurrency market is amongst the fastest-growing of all the financial markets in the world. Unlike traditional markets, such as equities, foreign exchange and commodities, cryptocurrency market is considered to have larger volatility and illiquidity. This paper is inspired by the recent success of using deep learning for stock market prediction. In this work, we analyze and present the characteristics of the cryptocurrency market in a high-frequency setting. In particular, we applied a deep learning approach to predict the direction of the mid-price changes on the upcoming tick. We monitored live tick-level data from $8$ cryptocurrency pairs and applied both statistical and machine learning techniques to provide a live prediction. We reveal that promising results are possible for cryptocurrencies, and in particular, we achieve a consistent $78\%$ accuracy on the prediction of the mid-price movement on live exchange rate of Bitcoins vs US dollars.
Andrew L. Detzel, Hong Liu, Jack Strauss, Guofu Zhou · 5 authors
Abstract What predicts returns on assets with âhardâtoâvalueâ fundamentals such as Bitcoin and stocks in new industries? We are the first to propose an equilibrium model that shows how technical analysis can arise endogenously via rational learning, providing a theoretical foundation for using technical analysis in practice. We document that ratios of prices to their moving averages forecast daily Bitcoin returns in and out of sample. Trading strategies based on these ratios generate an economically significant alpha and Sharpe ratio gains relative to a buyâandâhold position. Similar results hold for smallâcap, youngâfirm, and low analystâcoverage stocks as well as NASDAQ stocks during the dotcom era.