Since cryptocurrencies are becoming more widely used and accepted in the financial system, precise price forecasting is essential for optimizing bitcoin investments. In this research study, we evaluated various machine learning models, including linear regression (LR), decision tree regression (DT), random forest regression (RF), support vector regression (SVR), gradient boosting regression (GB), adaboost regression, extreme gradient boosting regression (XGR), light gradientboosting regression (LGBM), k-nearest neighbors regression (KNN), ridge, andlasso. Additionally, we incorporated two deep learning (DL) models, namely artificial neural networks (ANN) and convolutional neural networks (CNN), to forecast daily bitcoin prices (BP). The initial data was obtained from Kaggle, a well-known platform for data science projects, and we applied the min-max scaler technique for consistent scaling during preprocessing. To assess the predictive capabilities of the models, we utilized regression metrics such as root mean square error (RMSE), mean absolute error (MAE), and correlation coefficient (R). Based on our findings, the CNN model demonstrated the highest effectiveness in predicting BPs among the DL models, with an RMSE of 0.0543, MAE of 0.0324, and an R value of 0.960. In the case of machine learning models, the RF model outperformed others, achieving an RMSE of 0.0246 and MAE of 0.0561. Investors, scholars, and decision-makers may all gain from these findings’ insightful revelations about BP forecasting. Developing these models further, investigating different preprocessing methods, and expanding the analysis to other cryptocurrencies might be the main goals of future research.
Xi Deng, Huiming Zhu, S X Li, Zishan Huang · 5 authors
This study measures time-frequency liquidity and investigates the quantile connectedness of cryptocurrencies, decentralized finance, and non-fungible tokens (NFTs). The empirical results reveal that high-liquidity cryptocurrencies and yield-farming tokens are the main net spillover transmitters of low-liquidity cryptocurrencies’ downside networks in the short term. In addition, the connectedness between high-liquidity cryptocurrencies and yield-farming tokens significantly increases in the long-term upside network. Finally, NFTs exhibit substantial risk-bearing abilities.
An Pham Ngoc Nguyen, Tai Tan, Marija Bezbradica, Martin Crane
We employ graph-based methods to examine the connectedness between cryptocurrencies of different market caps over time. By applying denoising and detrending techniques inherited from Random Matrix Theory and the concept of the so-called Market Component, we are able to extract new insights from historical return and volatility time series. Notably, our analysis reveals that changes in volatility-based network structure can be used to identify major events that have, in turn, impacted the cryptocurrency market. Additionally, we find that these structures reflect investors’ sentiments, including emotions like fear and greed. Using metrics such as PageRank, we discover that certain minor coins unexpectedly exert a disproportionate influence on the market, while the largest cryptocurrencies such as BTC and ETH seem less influential. We suggest that our findings have practical implications for investors in different ways: Firstly, helping them to avoid major market disruptions such as crashes, to safeguard their investments, and to capitalize on opportunities for high returns; Secondly, sharpening and optimizing the portfolios thanks to the understanding of cryptocurrencies’ connectedness.
Asif Zaman, Issam Tlemsani, Robin Matthews, Mohamed Ashmel Mohamed Hashim
Purpose The rapid rise of Islamic crypto assets, underpinned by blockchain technology, has introduced a novel dimension to the Islamic financial landscape, raising questions about their potential as safe havens within emerging Islamic economies. However, the opportunities and challenges associated with this phenomenon remain insufficiently explored. In this context, this study aims to empirically investigate the extent to which blockchain technology can establish Islamic crypto assets as safe havens in equity markets within Islamic economies. Design/methodology/approach This study addresses the need for rigorous empirical analysis to understand the dynamics between Islamic crypto assets and stock markets in emerging Islamic economies, focusing on the transmission of volatility. While the evolving nature of the Islamic financial sector demands reliable data, the reliance on the most available data offers insights into the expected future trends in this emerging field. The research specifically focuses on three essential assets in the Islamic financial portfolio: OneGram Coin and X8XToken, both backed by gold and MRHB DeFi, an Islamic DeFi asset lacking gold backing. These crypto assets are compared with corresponding assets in seven stock markets of emerging Islamic economies. Using daily log returns of the Islamic crypto assets from various sources and seven Islamic stock indices. The data covers the period from December 27, 2021, to December 28, 2022, capturing the fluctuations in Islamic stocks and cryptocurrency markets during the post-COVID-19 era. This research uses advanced econometric techniques, including pairwise dynamic correlation and the DCC GARCH model. Findings The findings indicate that Islamic crypto assets exhibit distinct characteristics, with lower volatility and low correlations compared to their conventional counterparts in non-Islamic contexts. This outcome suggests that these Islamic crypto assets could potentially serve as safe havens within Islamic stock markets, offering valuable insights for various stakeholders, including investors, governments and policymakers. Research limitations/implications The findings are based on a specific set of Islamic crypto assets and may vary with a different selection. Market dynamics can also influence the relationships observed. Nevertheless, the outcomes provide valuable insights for investors, policymakers and researchers interested in the intersection of Islamic finance, cryptocurrency and technology. Originality/value In essence, this research not only unveils the potential of Islamic crypto assets as stabilizing forces but also delineates a trajectory for subsequent research endeavours within the realm of emerging Islamic Fintech, elucidating the challenges, opportunities and benefits that lie therein. With a discerning eye on circumventing the pitfalls entrenched within conventional crypto finance, this study contributes to a heightened comprehension of the transformative role that Islamic crypto assets can assume, ultimately enriching the financial resilience of Islamic economies.
Yang Junhua, Samuel Kwaku Agyei, Ahmed Bossman, Mariya Gubareva · 5 authors
To address ESG stock susceptibility to episodic shocks in financial markets, we use nonparametric quantile-based techniques applied to the 2014-2022 period. We (i) analyse the ability of traditional assets to predict ESG stocks returns, (ii) explore whether oil or gold serves as a safe haven for ESG stocks, and (iii) ascertain how ESG stocks respond to market sentiment, crypto-based uncertainty, and geopolitical risk (GPR). We find that gold, oil, market sentiment (tracked by the VIX), the implied volatility of crude oil (OVX) and GPR are significant predictors of ESG returns. None of gold or oil serves as a safe haven for ESG stocks, both acting just as diversifiers. In their turn, ESG could stocks hedge against the shocks from GPR and cryptocurrency-triggered market uncertainties in bearish states of the market. These findings are important for asset allocation and risk management, assisting investors in the already ongoing switch from ordinary to sustainable investments.
Abstract This study employs the Bayesian Networks (BN) and the wavelet coherence approaches to invest the relationship between Bitcoin volatility and financial asset classes (MSCI world equity index, S&P Goldman Sachs Commodity Index [GSCI], US index and Investment Grade Corporate Bond Index ETF [PIMCO]) using daily data for the period from August 2011 to October 2021. The results show that the causal relationship between Bitcoin and other financial assets varies depending on the market states. During the low volatility periods, Bitcoin has a stronger impact on the GSCI, while during the stability periods, it has a direct effect on the US index and the MSCI world index. In contrast, during high volatility periods, Bitcoin has a direct impact on both the GSCI and PIMCO indices. The key findings enabled us to provide implications for US investors to promote asset allocation and risk management covering both Bitcoin and traditional financial markets. The results suggest that policymakers should watch Botcoin closely to preserve financial stability.
This paper analyzes asset bubbles in the non-fungible token (NFT) and cryptocurrency markets, and assesses the impact of cryptocurrency prices and market sentiment on NFT bubble formation. We employ the Generalized Unit Root Test (GSADF test) to examine price bubbles across the NFT market, including sub-markets and related projects, as well as seven major cryptocurrencies. Our research identifies cryptocurrency bubbles in three distinct periods, with deflation observed in 2022. We establish a strong positive correlation between NFTs and most cryptocurrencies in terms of bubble dynamics. Notably, market sentiment indicators have varying effects on NFT bubbles; the VIX index has a positive impact, while the GEPU index and Google Trends data have negative effects. These findings provide valuable insights for regulators and investors into NFT bubble dynamics, cryptocurrency price behaviour, and market sentiment, facilitating informed decision-making.
In the realm of cryptocurrency forecasting, accurately predicting short-term Bitcoin log returns remains a challenging endeavor due to its inherent volatility and sensitivity to multifarious external factors. This study addresses this challenge by proposing an integrated approach that combines the capabilities of the TimesNet deep learning model with sentiment analysis techniques. TimesNet, specifically designed for time series data, has demonstrated proficiency in extracting salient patterns. When synergized with sentiment analysis, a more nuanced understanding of price determinants emerges. Preliminary results from our experiments indicate a significant enhancement in predictive accuracy within the Bitcoin market. Such advancements not only furnish investors and researchers with refined forecasting tools but also accentuate the burgeoning role of deep learning methodologies in the domain of financial forecasting.
The world is currently facing a major issue of high emissions from fossil-fuel-based energy sources, which contribute to the persistent problem of climate change. A switch to a renewable-powered infrastructure is necessary to mitigate this challenge. However, the shift to renewable energy faces obstacles, such as high costs and economic uncertainties. This work proposes mitigation of climate change by investigating the potential for bitcoin mining to serve as a means of utilizing surplus renewable energy from planned installations before grid integration. The study’s findings indicate the potential for bitcoin to provide economic benefits as an alternative to grid-powered mining at planned renewable installations across the U.S. states. We show that states like Texas have the maximum potential, with 32 planned renewable installations that could generate combined profits of $47M using bitcoin mining during precommercial operation.
Abstract This study contributes to the unconsolidated cryptocurrency literature, with a systematic literature review focused on cryptocurrency market microstructure. We searched Web of Science database and focused only on journals listed on 2021 ABS list. Our final sample comprises 138 research papers. We employed a quantitative and an integrative analysis, and revealed complex network associations, and a detailed research trending analysis. Our study provides a robust and systematic contribution to cryptocurrency literature by making use of a powerful and accurate methodology—the bibliographic coupling, also by only considering ABS academic journals, using a wider keyword scope, and not enforcing any restrictions regarding areas of knowledge, thus enhancing the contribution of extant literature by allowing the insights of more high-quality peripheral studies on the subject. The conclusions of this study are of extreme importance for researchers, investors, regulators, and the academic community in general. Our study provides high structured networking and clear information for research outlets and literature strands, for future studies on cryptocurrency investment, it also presents valuable insights to better understand the cryptocurrency market microstructure and deliver helpful information for regulators to effectively regulate cryptocurrencies.
Minority game theory has, traditionally, been used to simulate player behavior under various conditions in a number of stock markets. However, digital markets, such as cryptocurrencies, have been largely ignored by game theory models. Using a comparative approach, with data both from traditional equities markets and from Bitcoin this article presents a model of a dollar game and compares its outcome to real-life data. The paper aims to prove that game theory can be used to predict cryptocurrency markets similarly to how it is used to predict traditional stock markets. By using historical data from the London Stock Exchange and Bitcoin the paper demonstrates that a custom implementation of a dollar game can be used to predict general market trends and the overall impact of short-term investments in Bitcoin.
This paper investigates the persistence in the cryptocurrency market, focusing on five distinct groups categorized by their market capitalization during the sample period from 2020 to 2023. The study aims to test two hypotheses: (H1) The degree of persistence in the cryptocurrency market is contingent on market capitalization, and (H2) The efficiency of the cryptocurrency market has increased in recent years. The methodology employed for this examination is R/S analysis. The results indicate that the cryptocurrency market maintains its inefficiency, and no significant variations in persistence are discerned among different cryptocurrency groups, leading to the rejection of H1. Outcomes related to H2 present a nuanced scenario. Specifically, Litecoin and Ripple exhibit supportive evidence for the Adaptive Market Hypothesis, suggesting an improvement in the efficiency of the cryptocurrency market in recent years. A noteworthy revelation pertains to the anomaly observed in Bitcoin. Despite being the most capitalized and liquid cryptocurrency, it demonstrates inefficiency akin to levels observed five years ago. The implications of this study contribute to the comprehension of cryptocurrency market efficiency. The findings challenge the assumptions of the Efficient Market Hypothesis, favoring instead the Adaptive Market Hypothesis. For practitioners, the results hold significance, providing evidence of price predictability, particularly in the case of Bitcoin. This suggests that trend trading strategies remain viable for generating abnormal profits in the cryptocurrency market. Acknowledgments Alex Plastun gratefully acknowledges financial support from the Ministry of Education and Science of Ukraine (0121U100473).
Stock market performance is a challenging task due to high complexity and volatility in the financial markets There are many factors that influence the stock market and make it volatile. This research perform ordinary least square (OLS) to investigate the relationship between the wider Standard and Poor (S&P 500) US index, and the two independent variables, Bitcoin and gold prices. Daily time series data were collected from January 2015 to December 2022, with a total of 2011 daily observations, to determine whether gold and Bitcoin, or one of them, has a substantial impact on the S&P 500 index by using the Multiple Regression model. The results found that the S&P 500 market index is considerably impacted by both gold and Bitcoin, but gold has a larger impact on the S&P 500 Index than Bitcoin.
Abstract Since the onset of the COVID-19 pandemic, financial and commodity markets have exhibited significant volatility and displayed fat tail properties, deviating from the normal probability curve. The recent Russia-Ukraine war has further disrupted these markets, attracting considerable attention from both researchers and practitioners due to the occurrence of consecutive black swan events within a short timeframe. In this study, we utilized the Quantile-VAR technique to examine the interconnectedness and spillover effects between African equity markets and international financial/commodity assets. Daily data spanning from January 3, 2020, to September 6, 2022, was analyzed to capture tail risks. Our main findings can be summarized as follows. Firstly, the level of connectedness in returns is more pronounced in the lower and upper tails compared to the median. Secondly, during times of crisis, African equity markets primarily serve as recipients of systemic shocks. Lastly, assets such as Silver, Gold, and Natural Gas exhibit greater resilience to systemic shocks, validating their suitability as hedging instruments for African equities, in contrast to cryptocurrencies and international exchange rates. These findings carry significant implications for policymakers and investors in Africa equities.
This study investigates the influence of monetary policy and monetary policy uncertainties on Bitcoin returns, utilizing monthly data of BTC, and MPU from July 2010 to August 2023, and employing the Markov Switching Means VAR (MSM-VAR) method. The findings reveal that Bitcoin returns can be categorized into two distinct regimes: 1) regime 1 with low volatility, and 2) regime 2 with high volatility. In both regimes, an increase in MPU leads to a decline in Bitcoin returns: -0.028 in regime 1 and -0.44 in regime 2. This indicates that monetary policy uncertainty exerts a negative influence on Bitcoin returns during both downturns and upswings. Furthermore, the study explores Bitcoin's sensitivity to Federal Open Market Committee (FOMC) decisions.
This article explores the relationship between green energy and cryptocurrencies in the sustainable energy finance sector. The research findings contribute to our understanding of the application of green economy practice, enabling investors in financial markets, policymakers, and stakeholders to make informed decisions and develop specific strategies. Adopting the green economy paradigm makes it possible to promote collaboration and innovation by integrating ethical and responsible principles that can improve the overall quality of processes and boost sustainable growth. Cryptocurrencies have been widely used as financial instruments over the last decade. Given the development of the cryptocurrency market and the growing awareness of greener and more energy-efficient tokens, the green economy has become a popular topic for understanding economic and political issues. However, the literature still lacks clear evidence on how cryptocurrencies interact with green energies. Therefore, this study examines the long- and short-term relationships between dirty cryptocurrencies such as Bitcoin (BTC), Ethereum (ETH), clean cryptocurrencies such as Cardano (ADA), Ripple (XRP), Stellar (XLM), and green energies such as ISE Clean Edge Global Wind Energy, S&P Global Clean Energy, S&P TSX Renewable Energy and Clean Technology, Solactive China Clean Energy, in the period from January 2020 to September 2023. The results show that diversification is key, with clean cryptocurrencies such as ADA, XLM and XRP offering diversification opportunities alongside "dirty" cryptocurrencies such as BTC and ETH. Although sustainable energy indices show mixed evidence in the long and short term, they remain relevant for those who focus on clean energy investments. It is also becoming increasingly relevant for investors in sustainable portfolios to assess their environmental impact, especially for energy-intensive cryptocurrencies, and it is advisable to explore sustainable blockchain technologies.
Jinghua Wang, Geoffrey Ngene, Yan Shi, Ann Nduati Mungai
Policymakers and portfolio managers pay keen attention to sources of uncertainties that drive asset returns and volatility. The influence of uncertainty on Bitcoin has the potential to drive fluctuations in the entire cryptocurrency market. We investigate the predictability of thirteen economic policy uncertainty indices on Bitcoin returns. Using the Random Forest machine learning algorithm, we find that Singapore’s economic policy uncertainty (EPU) has the strongest predictive power on Bitcoin returns, followed by financial crisis (FC) uncertainty and world trade uncertainty (WTU). We further categorize these uncertainties into different groups. Interestingly, the predictability of uncertainty indices on Bitcoin returns within the international trade group is stronger compared to other uncertainty categories. Additionally, we observed that internet-based uncertainty measures have more predictive power of Bitcoin returns than newspaper- and report-based measures. These results are robust using various additional machine learning methods. We believe that these findings could be valuable for policymakers and portfolio managers when making decisions related to uncertainty drivers of cryptocurrency prices and returns.
José Antonio Núñez Mora, Mario Iván Contreras-Valdez, Roberto J. Santillán‐Salgado
This paper reports our findings on the return dynamics of Bitcoin and Ethereum using high-frequency data (minute-by-minute observations) from 2015 to 2022 for Bitcoin and from 2016 to 2022 for Ethereum. The main objective of modeling these two series was to obtain a dynamic estimation of risk premium with the intention of characterizing its behavior. To this end, we estimated the Generalized Autoregressive Conditional Heteroskedasticity in Mean with Normal-Inverse Gaussian distribution (GARCH-M-NIG) model for the residuals. We also estimated the other parameters of the model and discussed their evolution over time, including the skewness and kurtosis of the Normal-Inverse Gaussian distribution. Similarly, we determined the parameters that define the evolution of the estimated variance, i.e., the parameters related to the fitted past variance, square error and long-term average value. We found that, despite the market uncertainty during the COVID-19 emergency period (2020 and 2021), the selected cryptocurrencies’ return volatility and kurtosis were even greater for several other subperiods within our sample’s time frame. Our model represents an analytical tool that estimates the risk premium that should be delivered by Bitcoin and Ethereum and is therefore of interest to risk managers, traders and investors.
This paper aims to reveal the asymmetric co-integration relationship and asymmetric causality between Bitcoin and global financial assets, namely gold, crude oil and the US dollar, and make a comparison for their asymmetric relationship before and after the COVID-19 outbreak. Empirical results show that there is no linear co-integration relationship between Bitcoin and global financial assets, but there are nonlinear co-integration relationships. There is an asymmetric co-integration relationship between the rise in Bitcoin prices and the decline in the US Dollar Index (USDX), and there is a nonlinear co-integration relationship between the decline of Bitcoin and the rise and decline in the prices of the three financial assets. To be specific, there is a Granger causality between Bitcoin and crude oil, but not between Bitcoin and gold/US dollar. Before the outbreak of the COVID-19 pandemic, there was an Asymmetric Granger causality between the decline in gold prices and the rise in Bitcoin prices. After the outbreak of the pandemic, there is an asymmetric Granger causality between the decline in crude oil prices and the decline in Bitcoin prices. The COVID-19 epidemic has led to changes in the causality between Bitcoin and global financial assets. However, there is not a linear Granger causality between the US dollar and Bitcoin. Last, the practical implications of the findings are discussed here.
As an alternate form of trade money, cryptocurrencies are now widely accepted and have been integrated into all financial activities. Trading cryptocurrencies is one of the most popular and promising forms of investing. However, the cryptocurrency markets are notorious for their tremendous volatility and price discrepancies over short periods. To ensure accurate and trustworthy predictions, it is necessary to have an automated trading model that includes portfolio management and optimization. Automated algorithmic trading uses computers to carry out trades in accordance with the past and predicted trends following a defined set of rules. These rules include trading instructions based on time, value, quantity, or any other mathematical model of trading. Profits may be achieved through algorithmic trading at inhumanely high speeds and frequencies. In addition to providing profitable trading opportunities, algorithmic trading increases market fluidity and increases trading accuracy by reducing human elements such as emotions and feelings regarding the trade. This paper aims to contribute to the ongoing market revolution by discussing the various aspects of cryptocurrecy trading, its forecasting and actual development of an algorithmic trading bot that will implement client strategies closely accompanied by its own calculations for daily exchanges based on economic conditions and client approaches. It will also contribute to and exchange with ongoing adjustments throughout the day to ensure the best profitability of the clients.