David Iheke Okorie, Joel Miworse Gnatchiglo, Presley K. Wesseh
Active cryptocurrency mining and trading comes with heavy electricity demand and increased emissions. Thus, cryptocurrency mining is prohibited in most economies. Consequently, miners relocate to regions or economies without these prohibitions and/or with relatively lower electricity rates. As such, presenting a nexus between the cryptocurrency and electricity markets, even at the global level. This article investigates the different forms of relationships existing between these markets. The conditional asymmetric volatility model with the Wald, nonparametric and parametric Granger causality tests are employed. The results confirm the existence of both unidirectional and bidirectional lead-lag return relationships between the cryptocurrency and electricity markets. Cryptocurrency returns drive electricity demand. This finding is homogeneous both on a global and strata (homogeneous groupings) basis. Also, the electricity market spills over significant volatilities to the cryptocurrency markets without feedback, nonetheless. Result-based policies are recommended towards green finance, decarbonization, and emission mitigations through the demand for electricity by the cryptocurrency markets. They include the use of clean and renewable electricity sources and technologies for cryptocurrency market activities.
Decentralized finance (DeFi) is a brand-new disruptive procedure that encourages the use of blockchain technology for developing and distributing a variety of financial goods and services. This study investigates the time-varying and asymmetric interplay between DeFi and CEE stock returns, concentrated around the COVID-19 outbreak and the Russo-Ukrainian conflict. While the associations between other cryptocurrencies and conventional assets have been studied, DeFi assets have not. For this purpose, we employ the multivariate DECO-GARCH model and cross-quantilogram framework. The results reveal a positive equicorrelation between DeFi and CEE stock market returns. Notably, the influence of DeFi on CEE stock markets is greater during the COVID-19 outbreak and the Russo-Ukrainian conflict than in the other periods. Furthermore, the cross-quantilogram estimations uncover that CEE stock markets depend less on the DeFi market at longer lag lengths. This means that the diversification benefits of DeFi against CEE stock market returns are more important for long-run investment horizons. In general, our research offers a new understanding of dependence structures, which might help investors make better investment decisions and direct their trading strategies.
R. C. Bose, Jeevan Nagarkar, Sushant Malik, Nisha Bharti
Predictability of the various financial instruments can lead to more trust and investment. The study examines the long-term and causal relationship between various Nifty indices and the Ethereum cryptocurrency. This study considers the data from April 2015 to December 2022 in two phases, pre-covid and post-covid. Johansenâs cointegration test was used to determine if the vectors in the data set are cointegrated, using the Max-Eigen and Trace tests for evaluation. The Granger causality test was also used to explore the short-term causal relationship between Ethereum and the five Nifty indices. The study found that post-pandemic daily returns of stock market indices have developed a significant cointegration with the cryptocurrency over time. The Granger causality test results showed bi-directional relationships of Nifty 50, Nifty 200 and Nifty Next 50 with Ethereum and a unidirectional relationship between Nifty Auto and Ethereum. The non-linear results reveal a one-way relationship pre-covid and a bi-directional relationship post-covid except for Nifty Banks. Johansenâs cointegration test, both in the pre-and post-covid-era, indicated that these indices had a substantial long-term cointegration with cryptocurrencies. This study also offers guidance to investors in making long-term investment decisions and to regulatory authorities. This implied that the investing decisions resulted in developing a causal relationship between the equity market and cryptocurrencies, which seemed very unlikely before 2020. This indicates that a new and young investor also considered cryptocurrencies a viable alternate investment option compared to traditional options such as fixed deposits, gold, and other fixed-income instruments.
This research analyzes the dynamic relationships between the economic and political uncertainty index and the fear index in global markets and cryptocurrencies using the wavelet-based DCC-GARCH method, considering different time scales. Monthly data sets for the periods 2012âApril 2024 for GEPU,VIX, and Bitcoin and April 2016âApril 2024 for Ethereum are used in the study. Findings are obtained in terms of the volatility interaction between cryptocurrencies (Bitcoin and Ethereum) and GEPU and VIX, as well as four different time scales representing the short, medium, and long term. As a result of the analysis based on raw data, it was found that there is no volatility interaction between cryptocurrencies and GEPU and VIX returns. However, there is a volatility interaction between past volatility shocks and current period volatility shocks in the 4-8 and 16-32 month investment cycle periods of VIX, Bitcoin, GEPU, and Ethereum and time scales. These results, which show that volatility shocks persist in both 4-month and 16-month investment cycles, have significant implications for investors and policymakers. They highlight the need for comprehensive information about changes in the global economy and politics, and they are expected to provide insights for both investors and policymakers.
Majid Mirzaee Ghazani, Ali Akbar Momeni Malekshah, Reza Khosravi
Abstract We used daily return series for three pairs of datasets from the crude oil markets (WTI and Brent), stock indices (the Dow Jones Industrial Average and S&P 500), and benchmark cryptocurrencies (Bitcoin and Ethereum) to examine the connections between various data during the COVID-19 pandemic. We consider two characteristics: time and frequency. Based on Diebold and Yilmazâs (Int J Forecast 28:57â66, 2012) technique, our findings indicate that comparable data have a substantially stronger correlation (regarding return) than volatility. Per BarunĂk and KĆehlĂkâ (J Financ Econ 16:271â296, 2018) approach, interconnectedness among returns (volatilities) reduces (increases) as one moves from the short to the long term. A moving window analysis reveals a sudden increase in correlation, both in volatility and return, during the COVID-19 pandemic. In the context of wavelet coherence analysis, we observe a strong interconnection between data corresponding to the COVID-19 outbreak. The only exceptions are the behavior of Bitcoin and Ethereum. Specifically, Bitcoin combinations with other data exhibit a distinct behavior. The period precisely coincides with the COVID-19 pandemic. Evidently, volatility spillover has a long-lasting impact; policymakers should thus employ the appropriate tools to mitigate the severity of the relevant shocks (e.g., the COVID-19 pandemic) and simultaneously reduce its side effects.
This paper examines the correlation between three prospective investing options: the Bitcoin cryptocurrency price, gold, and the Dow Jones stock index. The main research question is whether there is a causal effect of gold and the DWJ on Bitcoin and how this effect varies on time. The study begins with a background analysis that explains the definitions and operation of cryptocurrencies, followed by a brief overview of gold and its derivatives. In addition, a historical review of stock markets is provided, with a focus on the Dow Jones index. Then, a literature review follows. Daily data from three separate periods are used, each spanning four years. The first period, running from October 2014 to September 2018, provides an overview of the introduction of official cryptocurrency price data. The second period, running from Oct 2018 to Sept 2022, captures more recent trends preceding COVID-19. The third period, from January 2020 to December 2023, is the whole COVID-19 period with the initiation, embedded, and terminal phases. Classical inductive statistical methods (descriptive, correlations, multiple linear regression) as well as time series analysis methods (autocorrelation, cross-correlation, Granger causality tests, and ARIMA modeling) are used to analyze the data. Rigorous testing for autocorrelation, multicollinearity, and homoskedasticity is performed on the estimated models. The results show a correlation of Bitcoin with gold and the DWJ. This correlation varies over time, as in the first period the correlation mainly concerns the DWJ and in the second it mainly concerns gold. By using ARIMA models, it was possible to make a forecast in a time horizon of a few days. In addition, the structure of the forecasting mechanism of gold and DWJ on Bitcoin seems to have changed during the COVID-19 crisis. The findings suggest that future research should encompass a broader dataset, facilitating comprehensive comparisons and enhancing the reliability of the conclusions drawn.
This study aims to investigate the information spillover among four traditional financial assets (i.e., crude oil, gold, stock, and U.S. dollar) and nine main cryptocurrencies (i.e., Bitcoin, Cardano, Dai, Ripple, Dogecoin, Ethereum, Ethereum Classic, Monero, and Tether), by constructing entropy-based information spillover network and information integration network from both static and dynamic perspectives. The empirical results show that the information spillover among these assets is time-varying, experiencing an obvious increase trend after the COVID-19. As a whole, traditional financial assets mainly play the role of net information transmitter while cryptocurrencies mainly play the role of net information recipient. Tether and Dai are the two main visual coins that can transmit net information flow to traditional assets, while gold and stock are the two main traditional assets that transmit net information flow to cryptocurrencies. Tether and U.S. dollar are the central nodes that link traditional financial assets and cryptocurrencies together.
Objective: This study investigates how Environmental, Social, and Governance (ESG) criteria can be integrated into cryptocurrency portfolio strategies, evaluating their performance across different market conditions and time periods. Theoretical Framework: This research is based on Modern Portfolio Theory (MPT) and principles of ESG investing. The study uses Markowitz's mean-variance optimization and the triple bottom line approach to understand the benefits of ESG integration in investment strategies. Method: The research involves a comparative analysis of various cryptocurrency portfolio strategies, including Buy-and-Hold, Simple Moving Average (SMA), MinVar, and MaxSharpe. Data was collected daily from October 1, 2016, to September 31, 2021. The study uses mean-variance analysis to assess risk-return profiles, incorporating ESG factors into the evaluation framework. Results and Discussion: The results show that the Buy-and-Hold strategy consistently yielded the highest returns across most portfolios. However, during volatile periods, strategies like MinVar and MaxSharpe provided better risk-adjusted returns. The discussion contextualizes these results within the theoretical framework, highlighting how ESG integration enhances risk management and aligns investments with sustainable development goals (SDGs). Research Implications: This research suggests that integrating ESG criteria into cryptocurrency portfolios can improve risk management and align investments with sustainability goals. These findings have practical implications for investment strategy development and sustainable finance practices. Originality/Value: This study offers a unique analysis of cryptocurrency portfolio strategies that incorporate ESG criteria. Its findings are relevant for influencing sustainable investment practices and optimizing cryptocurrency portfolios in line with ESG principles.
The emergence of Bitcoin Exchange-Traded Funds (ETFs) marks a significant milestone in the evolution of cryptocurrency investment. This research paper investigates the potential impact of Bitcoin ETFs on existing cryptocurrency exchanges, focusing on liquidity dynamics and institutional investment trends. By examining the mechanisms through which ETFs may draw liquidity away from direct Bitcoin exchanges, this study aims to shed light on the evolving landscape of cryptocurrency trading. Additionally, the paper explores the potential for Bitcoin ETFs to attract increased institutional investment in the cryptocurrency market, analyzing the factors that may contribute to this trend. Through a comprehensive analysis of market data and expert insights, this research provides valuable insights into the evolving relationship between Bitcoin ETFs and traditional cryptocurrency exchanges.
Purpose The purpose of this study is to examine Bitcoin's price behavior across market conditions, focusing on the influence of Bitcoin's historical prices, news sentiment and market indicators like oil prices, gold and the S&P index. The authors also assess the stability of Bitcoin-inclusive hedging portfolios under different market conditions, for example, bearish, bullish and moderate market states. Design/methodology/approach This study uses the Quantile Autoregressive Distributed Lag model to explore the effects of different factors on Bitcoin's prices across various market situations. This method allows for a detailed analysis of historical trends, investor expectations and external market influences on Bitcoin's price movements and systematic stability. Findings Key findings reveal historical prices and investor expectations significantly influence Bitcoin in all market scenarios, with news sentiment exhibiting substantial volatility. This study indicates that oil prices have minimal impacts on Bitcoin, whereas gold is a stabilizing asset in bear markets, with the S&P index influencing short-term fluctuations. At the same time, Bitcoin's volatility varies with market conditions, proving more efficient as a hedging tool in bear and stable markets than in bull ones. Originality/value This study highlights the intrinsic correlation between Bitcoin's prices, news sentiment and financial market indicators, enhancing understanding of Bitcoin's market dynamics. The authors demonstrate Bitcoin's weak direct correlation with commodities like oil, the stabilizing role of gold in crypto portfolios and the stock market's indirect effect on Bitcoin prices. By examining these factors' impacts across various market conditions, the findings offer strategies for investors to improve hedging and portfolio management in cryptocurrency markets.
Bitcoin price volatility fascinates both researchers and investors, studying features that influence its movement. This paper expends on previous research and examines time series data of various exogenous and endogenous factors: Bitcoin, Ethereum, S&P 500, and VIX closing prices; exchange rates of the Euro and GPB to USD; and the number of Bitcoin-related tweets per day. A period of three years (from September 2019 to September 2022) is covered by the research dataset. A two-layer framework is introduced tasked with accurately forecasting Bitcoin price. In the first layer, to account for complexities in the analyzed data, variational mode decomposition (VMD) extracts trends from the time series. In the second layer, Long short-term memory and hybrid Bidirectional long short-term memory networks were used to forecast prices several steps ahead. This work also introduced an enhanced variant of the sine cosine algorithm to tune the control parameters of VMD and both neural networks for attaining the best possible performance. The main focus is on combining VMD with modified metaheuristics to improve cryptocurrency closing value forecast. Two sets of experiments were conducted, with and without VMD. The results have been contrasted with models tuned by seven other cutting-edge optimizers. Extensive experimental outcomes indicate that Bitcoin price can be forecasted with great accuracy using selected features and time series decomposition. Additionally, the best model was analyzed, and Shapley values indicated that features such as EUR/USD exchange rates, Ethereum closing prices, and GBP/USD exchange rates, have a significant impact on forecasts.
The recent global crises have heightened financial market instability, surging the need for diversification, hedging, and safe haven assets to mitigate stock market risks. This study employs a Quantile Vector Autoregression (Q-VAR) approach to analyze the interconnectedness between gold-backed cryptocurrencies and G7 stock market indices during crises spanning from December 1, 2020, to July 5, 2023. Our findings indicate a robust association between digital gold and financial assets, with a total connectedness index (TCI) of 58.64%. Remarkably, G7 stock indices emerge as significant contributors to market fluctuations compared to digital assets, exerting influence ranging from 24% to 37%, thereby underscoring the potential of gold-backed cryptocurrencies for effective diversification strategies. Dynamic analysis during crises indicates the pivotal role of DGX as a safe haven, alongside identifying NIKKEI as a significant net receiver. Furthermore, the total net directional connectedness examination corroborates the status of gold-backed cryptocurrencies as net receivers, reaffirming their safe-haven abilities. Intriguingly, an in-depth examination across quantiles validates symmetrical dynamic connectedness, with G7 indices predominantly functioning as net transmitters of spillover. Our empirical findings underscore the compelling safe-haven potential in gold-backed cryptocurrencies, offering valuable insights for investors, policymakers, and portfolio optimization during turbulent market conditions.
This paper investigates the hedging and safe haven capacity of gold and Bitcoin against the G7 stock market indices during the COVID-19 pandemic, the Russia-Ukraine military conflict, and the Silicon Valley Bank collapse. Using a novel Quantile-VAR connectedness approach, the results show that, at the median quantile, both gold and Bitcoin act as effective hedges during normal market conditions and strong safe-haven assets during the three crises. Gold emerges as the most prominent safe haven asset, outperforming Bitcoin, especially during the war and the SVB collapse. Among the G7 stock market indices, the Japanese and the American stocks may be used as risk diversifiers during crises. As for the rest of the G7 stocks, they are regarded as ârisk-onâ investments. Next, we assessed the robustness of our results at various quantiles. We found them to be generally consistent with the outcomes obtained at the median quantile, with one exception related to the S&P500.The results show that the repercussions of the COVID-19 pandemic and the war are much stronger than the American banking crisis.
Abstract In the blockchain world, proof-of-work is the dominant protocol mechanism that determines the consensus of the ledger. The hashrate, a measure of the computational power directed toward securing a blockchain through proof-of-work consensus, is a fundamental measure of preventing various attacks. This study tests the causal relationship between the hashrate and the security outcome of the Bitcoin blockchain. We use vector error correction modeling to analyze the endogenous relationships between the hashrate, Bitcoin price, and transaction fee, revealing the need for an additional variable to achieve our aim. Employing a measure summarizing the growth of demand factors in the Bitcoin ecosystem indicates that hashrate fluctuations significantly influence security level changes. This result underscores the importance of the hashrate in ensuring the security of the Bitcoin blockchain.
Sergio Luis Nåñez Alonso, Javier Jorge-VĂĄzquez, Miguel Ăngel Echarte FernĂĄndez, David Sanz Bas
Abstract A number of financial bubbles have occurred throughout history. The objective of this study was to identify the main similarities between Bitcoin price behavior during bubble periods and a number of historical bubbles. Once this had been carried out, we aimed to determine whether the solutions adopted in the past would be effective in the present to reduce investorsâ risk in this digital asset. This study brings a new approach, as studies have previously been conducted analyzing the similarity of Bitcoin bubbles to other bubbles individually, but these were not conducted in such a broad manner, addressing different types of bubbles, and over such a broad time period. Starting from a dataset with 9967 records, a combined methodology was used. This consisted of an analysis of the standard deviations, the growth rates of the prices of the assets involved, the percentage increase in asset prices from the origin of the bubble to its peak and its fundamental value, and, finally, the bubble index. Lastly, correlation statistical analysis was performed. The results obtained from the combination of the above methods reveal the existence of certain similarities between the Bitcoin bubbles (2011, 2013, 2017, and 2021) and the tulip bubble (1634â1637) and the Mississippi bubble (1719â1720). We find that the vast majority of the measures taken to avoid past bubbles will not be effective now; this is due to the digital and decentralized nature of Bitcoin. A limitation of the study is the difficulty in making a comparison between bubbles that occurred at different historical points in time. However, the results obtained shed light and provide guidance on the actions to be taken by regulators to ensure the protection of investors in this digital asset.
Elie Bouri, Mahdi Ghaemi Asl, Sahar Darehshiri, David Gabauer
Abstract This paper examines the dynamics of the asymmetric volatility spillovers across four major cryptocurrencies comprising nearly 61% of cryptocurrency market capitalization and covering both conventional (Bitcoin and Ethereum) and Islamic (Stellar and Ripple) cryptocurrencies. Using a novel time-varying parameter vector autoregression (TVP-VAR) asymmetric connectedness approach combined with a high frequency (hourly) dataset ranging from 1st June 2018 to 22nd July 2022, we find that (i) good and bad spillovers are time-varying; (ii) bad volatility spillovers are more pronounced than good spillovers; (iii) a strong asymmetry in the volatility spillovers exists in the cryptocurrency market; and (iv) conventional cryptocurrencies dominate Islamic cryptocurrencies. Specifically, Ethereum is the major net transmitter of positive volatility spillovers while Stellar is the main net transmitter of negative volatility spillovers.
Abstract Cryptocurrencies have rapidly become popular as digital assets, and as the market evolves, it is of great importance to understand their volatility and risk behavior. They present specific challenges and opportunities given that are operating within a decentralized and fast-changing ecosystem. Thus, their volatility affects risk management, investment strategies, and market stability. Cryptocurrency volatility can create both opportunities and risks. While it can provide substantial returns, it also presents challenges in terms of investment strategy, regulatory frameworks, business operations, and economic stability. As the cryptocurrency market matures, itâs likely that solutions to manage volatility will evolve, but it remains a key concern for participants in the ecosystem. In this respect, the aim of the paper is to examine the volatility behavior of the main cryptocurrencies (Bitcoin, Ethereum, and Litecoin), for a recent period, i.e. from June 2018 to June 2023. Using both traditional and advanced GARCH models, the results show that these cryptocurrencies experience periods of high and low volatility, but there is no significant asymmetry effect in their responses. This suggests a balanced risk-return profile for investors. Furthermore, there is no evidence for risk premium within the sample, that is no link between risk and return. Additionally, past volatility has a greater impact on current volatility than new information, since GARCH coefficients are significantly higher than the ARCH coefficients. These insights can help investors, policymakers, and researchers to manage the cryptocurrency markets more effectively.
Abstract Research purpose. This study analysed the three cryptocurrencies with the largest market capitalization: Bitcoin, Ether (cryptocurrency built upon the Ethereum project's blockchain technology), and Binance coin, which account for 60% of the total cryptocurrency market capitalization. The purpose of this research was to measure the impact of monetary policy on the price of these cryptocurrencies using an adjusted R squared. Design / Methodology / Approach. As dependent variables, we used interest rates controlled by the European Central Bank and the Federal Reserve and reports from the European Central Bank and the Federal Open Market Committee. A robust Elastic Net Regression with Autoregressive Integrated Moving Average (ARIMA) residuals machine learning approach was applied to obtain robust regression coefficients and corresponding standard errors. To ascertain the robustness of the model, a technique known as rolling window cross-validation was employed. Findings. The results of this study show that monetary policy decisions and announcements significantly impact the price of cryptocurrencies. The impact on cryptocurrencies is likely to be significant both in the period of economic stability (2018-2020) and in the period of economic shocks (2020-2022). This relationship is likely to be indirect, acting through investor sentiment. Originality / Value / Practical implications. The results of this study may be useful to monetary policymakers, as they reveal the link between their actions and the price of cryptocurrencies. Our model will also be useful for mutual fund managers and private investors, as they can anticipate the price dynamics of cryptocurrencies when assessing monetary policy frameworks.
This paper evaluates the performance of the Long Short-Term Memory (LSTM) deep learning algorithm in forecasting Bitcoin and Ethereum prices during the COVID-19 epidemic, using their high-frequency price information, ranging from December 31, 2019, to December 31, 2020. Deep learning (DL) techniques, which can withstand stylized facts, such as non-linearity and long-term memory in high-frequency data, were utilized in this paper. The LSTM algorithm was employed due to its ability to perform well with time series data by reducing fading gradients and reliance over time. The obtained empirical results demonstrate that the LSTM technique can predict both Ethereum and Bitcoin prices. However, the performance of this algorithm decreases as the number of hidden units and epochs grows, with 100 hidden units and 200 epochs delivering maximum forecast accuracy. Furthermore, the performance study demonstrates that the LSTM approach gives more accurate forecasts for Ethereum than for Bitcoin prices, indicating that Ethereum is more prominent than Bitcoin. Moreover, the increased accuracy of forecasting the Ethereum price made it more reliable than Bitcoin during the COVID-19 coronavirus crisis. As a result, cryptocurrency traders might focus on trading Ethereum to increase their earnings during a crisis.
Abstract Non-fungible Tokens (NFTs), represent a revolution in the digital ownership paradigm. NFTs are a kind of digital asset built on blockchain technology, most commonly the Ethereum blockchain, that validate the uniqueness and ownership of a unique digital item in question. Each NFT carries specific information or attributes that make it original and non-fungible. Unlike cryptocurrencies like Bitcoin or Ethereum, which are identical to each other, non-fungible tokens cannot be exchanged on a like-for-like basis making them non-fungible. NFTs are traded for cryptocurrencies via online trading platforms. Investment in NFTs can present a risky situation due to the large volatility of the assets in a quite short time. This article focuses on identification of key aspects that influence decision making process of potential investors who are considering buying non-fungible tokens as an investment tool in the Czech Republic. From the point of view of investment decision-making, the primary factors appear to be the expected income from the investment, its payback period, and the risk that the investor undertakes. It has been proven that there is a degree of dependence between gender and the mentioned decision-making factors. The research showed that men are more inclined to make decisions based on expected returns, while women are more likely to make decisions based on perceived risk.
Disclosure and transparency are two critical components in the green financing sector, especially the green bond segment. Compared to green instruments like green credit, green bond issuances facilitate information dissemination and reduce information asymmetry. Still, concerns stemming from numerous macro-level and firm-level factors impede market advancement. Investors are restrained from green bond financing owing to a fear of potential greenwashing. The nascency of the market, resulting in inadequate disclosure regimes and measurement challenges, exacerbates the problem. Can we find a solution to tackle the dilemma of greenwashing and information asymmetry using emerging, sophisticated technologies? Assessing the major theoretical underpinnings, this chapter presents a comprehensive landscape of how technologies like distributed ledger technologies, blockchain, the internet of things, artificial intelligence, machine learning, and the like fit into the green debt market. While following a theoretical approach, collating research, and the green bond market developments, the authors initiate an investigation into how technology can manage disclosure biases. The assessment signifies the role of technology, specifically FinTech, blockchain, and AI technologies, in spotting greenwashing and information asymmetry.
ÎΔÏÏγία ÎÎżÏ ÏΜαÏÎ¶ÎŻÎŽÎżÏ , Dimitrios Farazakis, Ioannis Mallidis, Christos Floros
This research conducted a thorough investigation of Bitcoin volatility patterns using three interrelated methodologies: R/S investigation, simple moving average (SMA), and the relative strength index (RSI). The paper jointly employes the above techniques on volatility range-based estimators to effectively capture the unpredictable volatility patterns of Bitcoin. R/S analysis, SMA, and RSI calculations assess time series data obtained from our volatility estimators. Although Bitcoin is known for its high volatility and price instability, our analysis using R/S analysis and moving averages suggests the existence of underlying patterns. The estimated Hurst exponents for our volatility estimators indicate a level of persistence in these patterns, with some estimators displaying more persistence than others. This persistence underscores the potential of momentum-based trading strategies, reinforcing the expectation of additional price rises after declines and vice versa. However, significant volatility often interrupts this upward movement. The SMA analysis also demonstrates Bitcoinâs susceptibility to external market forces. These observations indicate that traders and investors should modify their risk management approaches in accordance with market circumstances, perhaps integrating a combination of momentum-based and mean-reversion tactics to reduce the risks linked to Bitcoinâs volatility. Furthermore, the existence of robust patterns, as demonstrated by our investigation, presents promising opportunities for investing in Bitcoin.
Abstract We study the statistical properties of the Bitcoin return series and provide a thorough forecasting exercise. Also, we calibrate stateâofâtheâart machine learning techniques and compare the results with econometric time series models. The empirical assessment provides evidence that the application of machine learning techniques outperforms econometric benchmarks in terms of forecasting precision for both inâ and outâofâsample forecasts. We find that both deep learning architectures as well as complex layers, such as LSTM, do not increase the precision of daily forecasts. Specifically, a simple recurrent neural network describes a sensible choice for forecasting daily return series.
The bubbles and spikes in cryptocurrency prices increase considerably the risk on investments in these assets. In the traditional time series literature bubbles are viewed as nonstationary and non-estimable components of a process. In this paper, we adopt a different approach and consider the bubbles as inherent features of a strictly stationary causal-noncausal (mixed) Vector Autoregressive (VAR) process. This approach allows us to model and estimate the common bubbles and spikes in cryptocurrency prices. It also provides us linear combinations of cryptocurrencies that eliminate common bubbles analogously to the cointegrating vectors eliminating common trends in unit root processes. They are used to build cryptocurrency portfolios immune to the risk of common bubbles that ensure stable investment strategies. The mixed VAR model is estimated from the US Dollar prices of Bitcoin, Ethereum, Ripple, and Stellar over the period 2017â2019. We document the common bubbles and illustrate the behavior of bubble-free portfolios.