Abstract This study analyses six major cryptocurrencies and four global stock markets to explore the role of cryptocurrencies as a hedge, safe haven, and diversifier in stock markets. The study employs ADCCâGARCH and Wavelet Coherence Technique, using daily data from 4 January 2017 to 28 February 2023. The study has found that stock returns and unstable cryptocurrency returns have high volatility persistence in the long run. Besides, while unstable digital currencies (Bitcoin, Ethereum, Binance Coin, and Dogecoin) serve as a hedge during stable economic periods, they have not been a hedge during economic turmoil in the stock markets. Conversely, stablecoins (Tether and USD Coin) have been shown to have acted as a hedge during normal economic times and have offered a safe haven during economic downturns. Except for Tether, all cryptocurrencies' diversification capacity is timeâvarying. In stable economic conditions, they serve as diversifiers, but during turmoil, they do not. However, Tether serves as a diversifier regardless of the financial situation. Finally, the present investigation is expected to offer crucial information on hedge, safe haven and diversification for quasiâinvestors.
Using daily closing price observations between November 2017 and February 2023, this paper documents how the shocks of a cryptocurrency ETF resonate with ETFs representing traditional asset classes in terms of price and volatility. We find price transmission from the cryptocurrency ETF into the ETFs of several currencies, small-cap equities, and inflation. Risk propagation from the cryptocurrency ETF flows toward ETFs constituted of equities of various sizes, oil prices, high-yield corporate bonds, and inflation. There is scant evidence of transmission from ETFs with underlying conventional assets into the cryptocurrency ETF. The findings bear implications for low-cost risk management strategies.
Fatma Ben Hamadou, Taicir Mezghani, Ramzi Zouari, Mouna BoujelbĂšne Abbes
Purpose This study aims to assess the predictive performance of various factors on Bitcoin returns, used for the development of a robust forecasting support decision model using machine learning techniques, before and during the COVID-19 pandemic. More specifically, the authors investigate the impact of the investor's sentiment on forecasting the Bitcoin returns. Design/methodology/approach This method uses feature selection techniques to assess the predictive performance of the different factors on the Bitcoin returns. Subsequently, the authors developed a forecasting model for the Bitcoin returns by evaluating the accuracy of three machine learning models, namely the one-dimensional convolutional neural network (1D-CNN), the bidirectional deep learning long short-term memory (BLSTM) neural networks and the support vector machine model. Findings The findings shed light on the importance of the investor's sentiment in enhancing the accuracy of the return forecasts. Furthermore, the investor's sentiment, the economic policy uncertainty (EPU), gold and the financial stress index (FSI) are the top best determinants before the COVID-19 outbreak. However, there was a significant decrease in the importance of financial uncertainty (FSI and EPU) during the COVID-19 pandemic, proving that investors attach much more importance to the sentimental side than to the traditional uncertainty factors. Regarding the forecasting model accuracy, the authors found that the 1D-CNN model showed the lowest prediction error before and during the COVID-19 and outperformed the other models. Therefore, it represents the best-performing algorithm among its tested counterparts, while the BLSTM is the least accurate model. Practical implications Moreover, this study contributes to a better understanding relevant for investors and policymakers to better forecast the returns based on a forecasting model, which can be used as a decision-making support tool. Therefore, the obtained results can drive the investors to uncover potential determinants, which forecast the Bitcoin returns. It actually gives more weight to the sentiment rather than financial uncertainties factors during the pandemic crisis. Originality/value To the authorsâ knowledge, this is the first study to have attempted to construct a novel crypto sentiment measure and use it to develop a Bitcoin forecasting model. In fact, the development of a robust forecasting model, using machine learning techniques, offers a practical value as a decision-making support tool for investment strategies and policy formulation.
Abstract The ınvestment decisions of institutional and individual investors in financial markets are largely influenced by market uncertainty and volatility of the investment instruments. Thus, the prediction of the uncertainty and volatilities of the prices and returns of the investment instruments becomes imperative for successful investment. In this study we seek to identify the best fit model that can predict the volatility of return of Bitcoin, which is in high demand as an investment tool in recent times. Using the opening data of weekly Bitcoin prices for the period of 11.24.2013â03.22.2020, their logarithmic returns were calculated. The stationarity properties of the Bitcoin return series was tested by applying the ADF unit root test and the series were found to be stationary. After reaching the average equation model as ARMA (2.2), it was tested whether there was an ARCH effect in the ARMA (2,2) model. As a result of the applied ARCH-LM test, it is reached that the residuals of the average equation model selected have ARCH effect. Volatility of Bitcoin return series after detection of ARCH effect has been tried to predict with conditional variance models such as ARCH (1), ARCH (2), ARCH (3), GARCH (1,1), GARCH (1,2), GARCH (1,3), GARCH (2,1), GARCH (2,2), EGARCH (1,1) and EGARCH (1,2). While the obtained findings indicate that the best model is in the direction of GARCH (1,1) according to Akaike info criterion, it was found that GARCH (1,1) model does not have ARCH effect as a result of the applied ARCH-LM test. Thus, our empirical findings highlight an ample guide on appropriate modeling of price information in the Bitcoin market.
This paper presents an approach for predicting the price of Bitcoin using machine learning techniques. We used historical data of Bitcoin prices and extracted relevant features such as trading volume, social media sentiment, and market capitalization to train and test the models. Numerous machine learning algorithms, such as random forest, gradient boosting, and neural networks, were tested by us and evaluated their performance using metrics such as mean squared error and accuracy. Our results show that machine learning models can effectively predict the price of Bitcoin with a reasonable degree of accuracy. We also discuss the limitations of our approach and suggest future research directions to improve the performance of Bitcoin price prediction models. Our findings suggest that machine learning can be a useful tool for investors and traders in making informed decisions about Bitcoin investments.
Abstract This study investigates the herding behavior in the cryptocurrency market during the period of the Russia and Ukraine conflict using intraday cryptocurrency price data of the five largest cryptocurrencies in terms of market capitalization. The empirical results indicate an anti-herding behavior during the whole period of the conflict, especially after the conflict officially happens. The research contributes to the growing literature on herding behavior in the cryptocurrency market by using intraday data and examining the RussiaâUkraine conflict period.
Leonardo H.S. Fernandes, JOSà W. L. SILVA, Aurelio F. Bariviera, Kleber E S Sobrinho · 5 authors
This paper sheds light on the changes suffered in cryptocurrencies due to the COVID-19 shock through a non-linear cross-correlations and similarity perspective. We have collected daily price and volume data for the seven largest cryptocurrencies considering trade volume and market capitalization. For both attributes (price and volume), we calculate their volatility and compute the Multifractal Detrended Cross-Correlations (MF-DCCA) to estimate the complexity parameters that describe the degree of multifractality of the underlying process. We detect (before and during COVID-19) a standard multifractal behaviour for these volatility time series pairs and an overall persistent long-term correlation. However, multifractality for price volatility time series pairs displays more persistent behaviour than the volume volatility time series pairs. From a financial perspective, it reveals that the volatility time series pairs for the price are marked by an increase in the non-linear cross-correlations excluding the pair Bitcoin vs Dogecoin (à ”Ă»Œ à ”Ă±„à ”Ă±Š (0) = â1.14%). At the same time, all volatility time series pairs considering the volume attribute are marked by a decrease in the non-linear cross-correlations. The K-means technique indicates that these volatility time series for the price attribute were resilient to the shock of COVID-19. While for these volatility time series for the volume attribute, we find that the COVID-19 shock drove changes in cryptocurrency groups.
Given the volatile nature of cryptocurrencies, accurately forecasting cryptocurrency volatility and understanding its determinants are crucial. This paper applies machine learning (ML) techniques to forecast cryptocurrency volatility using internal determinants (e.g., lagged volatility, previous trading information) and external determinants (e.g., technology, financial, and policy uncertainty factors). Both Random Forest and Long Short-Term Memory (LSTM) networks significantly outperform traditional volatility models such as GARCH. Furthermore, we explore two optimization modelsâGenetic Algorithm and Artificial Bee Colonyâto tune the hyper-parameters of LSTM. Our results indicate that the application of these optimization models substantially improves forecasting performance. Moreover, using SHapley Additive exPlanations, an interpretation method, we find that internal determinants play the most important roles in volatility forecasts. Finally, our results show that models trained with determinants from multiple cryptocurrencies outperform those trained with determinants from a single cryptocurrency, suggesting that considering a broader range of determinants can capture the complex dynamics in the cryptocurrency market.
Abstract This study measures the convergence and divergence of major cryptocurrencies by applying two distance measures used in machine learning. Particularly, the time-varying Euclidean distance measure was constructed by combining the first four moments (i.e. mean, variance, skewness and kurtosis) of the return distributions of cryptocurrencies following the $$\ell ^{2}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msup> <mml:mi>â</mml:mi> <mml:mn>2</mml:mn> </mml:msup> </mml:math> -normalisation. It was found that major cryptocurrencies converged to the centroid during the 2018 market crash, but diverged before and after the crash. Their divergence could be due to the uncertainty arising from market news and regulatory events. In addition, Bitcoin cosine similarity measure was developed to provide further insights into the relationship between Bitcoin and other cryptocurrencies. This cosine similarity shows how each cryptocurrency moves relative to Bitcoin, which is not captured by the Euclidean distance. More importantly, it was demonstrated that the divergence of major cryptocurrencies from their centroids can improve Markowitzâs efficient frontier and provide more diversification benefits to investors and portfolio fund managers. Finally, a profitable trading strategy was provided based on the Euclidean distance.
Bitcoin is a peer-to-peer form of digital currency proposed in 2008. Unlike other currencies, Bitcoin does not rely on a specific institution to issue it, it is based on a specific algorithm that generates it through a large number of calculations. In some countries, government agencies, central banks and academia regard Bitcoin is a virtual currency rather than a currency. This is because of Bitcoinâs high volatility, which does not have the two basic functions of the unit of account and the store of value that are unique to the currency. In recent years, Bitcoin has seen increasing media coverage and other cryptocurrency portfolios, as well as the significant capital gains have been seen in the high volatility environment. In this paper, we shed light on the low correlation of Bitcoin with traditional investment assets, making Bitcoin a potentially high-quality source of portfolio diversification. The results of the finding suggest that Bitcoin investments offer significant diversification benefits and should be included in optimal portfolios. In addition to this, we find that hedging strategies involving gold, oil, stocks and Bitcoin significantly reduce portfolio risk.
This study investigates the co-movement patterns of Asia technology stock indices and cryptocurrencies during the COVID-19 pandemic. The analysis examines Bitcoin and Ethereum, Chinaâs Tech index (XA90), and Indiaâs Tech index (NSEIT) from 2017 to 2021, representing both before and during COVID-19. To visually explore the co-movement between these variables, a bi-wavelet method is employed. This approach allows for an examination of how these variables move together over time coherently. There were noticeable changes in the co-movement patterns between technology stock indices and cryptocurrencies during COVID-19 compared to before the pandemic. The duration of co-movements decreased significantly after the emergence of COVID-19. The previous financial crisis had a longer time horizon for joint movement, lasting 256 days. However, during the pre-COVID-19 period, XA90 exhibited a strong co-movement with Bitcoin over this extended period but weakened afterward when COVID-19 emerged. Conversely, NSEIT showed a significant co-movement with both Ethereum and Bitcoin in the initial stages of the pandemic. Before that period, NSEIT had muted price movements along with BTC. These changes in price co-movements suggest shifts in herding behavior due to the pandemic. Notably, cryptocurrency markets have demonstrated faster recovery compared to technology stock markets.
In today's world, with the internet and finance closely integrated, the global-ization of cryptocurrency has deepened, prompting people to pay more atten-tion to the impact of cryptocurrency on the entire financial market. This pa-per provides a comprehensive review of relevant literature from five aspects: the development of cryptocurrency, price changes, the impact of cryptocur-rency on the stock market, the impact of cryptocurrency on the banking in-dustry, and the currency and commodity characteristics of cryptocurrency. The author also compares the price curves (in USD) of the S&P 500, ETH, and BTC from March 21, 2022, to March 21, 2023, and hopes to gain in-sights into the relationship between stocks and cryptocurrencies. Our re-search shows that the emergence of cryptocurrency has had a significant im-pact on the financial market, particularly in the banking industry. Although the emergence of cryptocurrency has added vitality to the financial market and increased investment options, the instability of cryptocurrency has also brought risks to investors. As the cryptocurrency market continues to ex-pand, policymakers and investors need to understand its potential impact on traditional financial instruments and the broader economy.
Abstract The cryptocurrency crash on the 5th of September, 2018, resulted in price decreases in 95 of the 100 leading digital currencies. We obtained millisecond data of some of the more prominent cryptocurrenciesâbitcoin, ethereum, ripple, bitcoin cash and eosâand some of the smaller cryptocurrenciesâneo, nem, omg, tezos and liskâthat were most affected in the crash and investigated what caused the digital market to collapse. We find that the behaviour of the more prominent cryptocurrencies and bitcoin, in particular, was the dominant factor behind the crash. We also find that smaller cryptocurrencies followed the behaviour of the larger ones in the crash. Furthermore, our empirical findings show that the trading behaviour of cryptocurrency traders (CTs) did not trigger the digital market crash. We propose the introduction of a single-cryptocurrency circuit breaker most prominent largest cryptocurrencyâbitcoinâthat will halt trading during market disruptions.
The knowledge of the interconnectedness between liquid and futures markets of cryptocurrencies amidst dynamic contemporary environment can be enriched through the full characterization of the direction, persistence and intensity of information flows between these markets. So, the present study attempts to investigate the static and dynamic connexions between liquid and futures markets of Bitcoin, Ethereum, Litecoin, Ripple XRP and Bitcoin Cash from June 2018 to June 2022. The connexion between their liquid and futures markets is first investigated using unconditional correlation, Johansenâs cointegration, vector error correction and Waldâs block exogeneity. Their estimates discern connexions encompassing significant long-run relationships between their liquid and futures markets; momentous unidirectional long-run causality from their futures market to liquid market; and momentous bidirectional short-run causality from their liquid market to futures market and from their futures market to liquid market. The present treatise encompasses methodological advancement in the investigation of interconnectedness between these markets by employing a dynamic conditional correlation model and a wavelet transform framework. Their discerned estimates indicate that the markets of Bitcoin, Litecoin, Ethereum and Bitcoin Cash have only momentous long-run perseverance, lingering and spillover effects of shocksâ sway on conditional correlations. However, there is momentous short- and long-run perseverance, lingering and spillover effects in the case of Ripple XRP. The wavelet coherence analysis also confirms these results by indicating a bidirectional short-run causal relation and a long-run positive comovement between liquid returns and futures returns of these cryptocurrencies. These discernments may help investors, portfolio managers and policymakers to enhance hedging effectiveness through optimal portfolio allocation and monitor financial contagion to attain and sustain financial stability in economies.
Bitcoin has attracted significant attention from academia and industry and has emerged as a new and rapidly growing research field over the past decade. However, there has been no previous bibliometric analysis of Bitcoin-related publications within business, management, finance, and economics. Consequently, the study conducts a bibliometric analysis of 1109 articles written in English language in the Scopus database, published between years 2020 to 2022, focusing on Bitcoin research within the domains of business, management, finance, and economics. This bibliometric analysis was performed using R and VOSviewer. The analysis explores publication trends, influential authors/institutions/countries, and significant articles in the field. The results provide valuable insights into the evolution and trends of Bitcoin research and offer guidance for researchers aiming to publish in reputable journals. The future research agenda includes investigating price volatility and risk analysis, exploring market inefficiency and price discovery mechanisms, understanding acceptance factors, studying governance and regulations, and examining business applications. Addressing these areas will contribute to a better understanding of Bitcoin's dynamics, its impact on financial markets, and its integration into traditional financial systems.
This study explores the stylized facts, volatility clustering, other highly irregular behaviour, and risk measures of cryptocurrenciesâ returns. By analysing bitcoin, ripple, and ethereum daily data we establish evidence of strong dependencies among analysed cryptocurrencies. This paper provides new insights about cryptocurrency behaviour and the main measures of risk and detailed comparative analysis with tech-stocks. Comprehensive research on stylized facts confirmed high risk for both cryptocurrencies and tech-stocks with cryptocurrencies being even riskier. Empirical research findings are useful in developing dependence and risk strategies for investment and hedging purposes, especially during more volatile periods in the markets as there was confirmed existence of volatility clusters when high volatility periods are followed by low volatility periods. Sensitivity analysis and measures of Value-at-Risk (VaR) and Expected Shortfall (ES) show the amount of losses investors can expect in the worst case scenario. Our results confirm the existence of predictability, volatility clustering, and possibilities for arbitrage opportunities. Findings could be beneficial for investors and policymakers as well as for scientific purposes as findings give us a better understanding of the behaviour of cryptocurrencies.
Ethereum is a major public blockchain. Besides being the second-largest digital currency by market capitalization for its cryptocurrency, the Ether (Î), it is also the foundation of Web3 and decentralized applications, or DApps, that are fuelled by Smart Contracts. At the time of this writing, Ethereum still uses Proof of Work (PoW) consensus algorithm to ensure the integrity of the blockchain and to prevent double spend. PoW requires the participation of miners, who are incentivized to assemble blocks of transactions by being rewarded with cryptocurrency paid by transaction originators and by the blockchain network itself via newly minted Î. Network fees for transaction submissions are called gas, by analogy to the fuel used by cars, and are negotiable. They are also highly volatile and hence it is critical to predict the direction they are heading into, so that one can time transaction submissions, when feasible. There have been several efforts to predict gas prices, including usage of large Mempools, analysis of committed blocks, and more recent ones using Facebook's Prophet model [Taylor, S. J., & Letham, B. (2017). Forecasting at scale. PeerJ Preprints, 5, e3190v2. https://doi.org/10.7287/peerj.preprints.3190v2]. In this study, we introduce an innovative approach that employs the DeepAR [Salinas, D., Flunkert, V., Gasthaus, J., & Januschowski, T. (2020). Deepar: Probabilistic forecasting with autoregressive recurrent networks. International Journal of Forecasting, 36(3), 1181â1191. https://doi.org/10.1016/j.ijforecast.2019.07.001] model, known for its superior forecasting accuracy over conventional methods by virtue of its ability to learn from multiple related time series. This methodology not only offers immediate advantages but also holds promise for ongoing enhancements. We substantiate our claims through empirical testing, utilizing data extracts from the Ethereum blockchain and cryptocurrency price feeds. This document is an extended version of our ICCS 2022 paper on the same topic. In this paper, we dive deeper into the internals of DeepAR forecasting algorithm [Salinas, D., Flunkert, V., Gasthaus, J., & Januschowski, T. (2020). Deepar: Probabilistic forecasting with autoregressive recurrent networks. International Journal of Forecasting, 36(3), 1181â1191. https://doi.org/10.1016/j.ijforecast.2019.07.001], analyse the correlation between the on-chain/off-chain sample data, and describe additional experiments that empirically prove our findings and, finally, perform a comparison of our outputs with those from the Prophet [Taylor, S. J., & Letham, B. (2017). Forecasting at scale. PeerJ Preprints, 5, e3190v2. https://doi.org/10.7287/peerj.preprints.3190v2] model.