The article aims to explore the heterogeneous feature in the determination of Bitcoin volatility using a Markov regime-switching model and test its forecasting ability. The forecasting methodology of the risk measurement of Bitcoin’s returns is based on the Conditional Autoregressive Value at Risk models (CAViaR) approach. Our results show that Bitcoin’s volatility is significantly related to the volatility of the crypto-asset’s return and the main determinants of volatility are speculation, investor attention, market interoperability and the interaction between speculation and market interoperability. In addition, we present evidence that investors’ attention is the main source of volatility. Speculation and the interaction term are related in a “U-shaped” form, whereas investor attention and market interoperability show a linear trend on the volatility of Bitcoin.
Increasing fluctuations in pricing and having great profit potential, utilization in advanced machine learning technologies to make robust predictions of cryptocurrencies especially bitcoin have attracted great attention in recent years. In this study, various statistical techniques; Moving Average Analysis and Autoregressive Integrated Moving Average and machine learning (ML) techniques; Artificial Neural Network, Recurrent Neural Network (RNN) and Convolutional Neural Network have been conducted and compared to predict the future value of Bitcoin cryptocurrency price. They have been applied for the univariate time series analysis with a window size of 32. To prove the usefulness of ML algorithms, and to show that the results of RNN is a better, mean squared error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) indicators have been applied. The study revealed that recurrent neural network yields better results than other methods in predicting daily Bitcoin price in terms of MSE, MAE and MAPE metrics. Besides, Wilcoxon-Mann-Whitney nonparametric statistic test is applied to test the performance between ARIMA and machine learning algorithms.
The paper provides a detailed understanding about what exactly Bitcoin (BTC) is. It also answers the question about where and how to use bitcoin as a consumer. The paper elaborates about how bitcoin can be earned and generated along with an ease to understand explanation about its technology. The objective of the paper is to identify whether BTC is still a feasible asset to make an investment in as compared with other existing securities and assets for both short term and long-term investors in the global market. The purpose is to figure out if bitcoin has potential in 2020 and coming years and will it yield high returns even after it has seen a price drop in 2019. Bitcoin became popular when its price peaked to almost $20000 in 2017. Global investors not only look at BTC in short term speculative prospective but also as a long-term investment asset hence it is called as the Digital Gold. BTC is also considered to be highly volatile in nature which is why studying the risk factor involved in investing in it becomes very important. Both mean variance approach and correlation approaches are used to evaluate the risk involved in BTC as an asset and comparison is made with other popular global assets to see if investing in Bitcoin is an ideal option or not.
The development process in financial markets give rise to the emergence of various financial instruments and cryptocurrencies, which are the newest tools of this process, are trying to integrate into the system. Even though the use of crypto-currencies for investment and speculation has increased, limited information on the market leads to high level of volatility in price and return. Therefore, this study aims to analyze the volatility dynamics of the returns of Bitcoin, which is the cryptocurrency with the largest market volume, using the weekly data set for 2013:04-2020:09 period. In this context, Exponential Generalized Autoregressive Conditional Heteroscedasticity (EGARCH) model is employed to investigate the asymmetric volatility, which refers to the asymmetric effects of positive and negative shocks. The results of the analysis show that the leverage effect applies to Bitcoin returns. In other words, the asymmetric effect between good and bad news is revealed. Moreover, the fact that the parameter of the volatility resistance has a high value reflects that the asymmetric past period shocks have a significant effect on the current period conditional variance.
Time series prediction plays a significant role in the Bitcoin market because of volatile characteristics. Recently, deep neural networks with advanced techniques such as ensembles have led to studies that show successful performance in various fields. In this paper, an ensemble-enabled Long Short-Term Memory (LSTM) with various time interval models is proposed for predicting Bitcoin price. Although hour and minute data set are shown to provide moderate shifts, daily data has relatively a deterministic shift. As such, the ensemble-enabled LSTM network architecture learned the individual characteristics and impact on price predictions from each data set. Experimental results with real-world measurement data show that this learning architecture effectively forecasts prices, especially in risky time such as sudden price fall.
Sérgio Adriani David, Claudio Marcio Cassela Inacio, Rafael Amorim Belo Nunes, J. A. Tenreiro Machado
Introduction: Cryptocurrencies have been attracting the attention from media, investors, regulators and academia during the last years. In spite of some scepticism in the financial area, cryptocurrencies are a relevant subject of academic research. Objectives: In this paper, several tools are adopted as an instrument that can help market agents and investors to more clearly assess the cryptocurrencies price dynamics and, thus, guide investment decisions more assertively while mitigating risks. Methods: We consider three methods, namely the Auto-Regressive Integrated Moving Average (ARIMA), Auto-Regressive Fractionally Integrated Moving Average (ARFIMA) and Detrended Fluctuation Analysis, and three indices given by the Hurst and Lyapunov exponents or the Fractal Dimension. This information allows assessing the behaviour of the time series, such as their persistence, randomness, predictability and chaoticity. Results: The results suggest that, except for the Bitcoin, the other cryptocurrencies exhibit the characteristic of mean reverting, showing a lower predictability when compared to the Bitcoin. The results for the Bitcoin also indicate a persistent behavior that is related to the long memory effect. Conclusions: The ARFIMA reveals better predictive performance than the ARIMA for all cryptocurrencies. Indeed, the obtained residual values for the ARFIMA are smaller for the auto and partial auto correlations functions, as well as for confidence intervals.
Alexander Brauneis, Roland Mestel, Ryan Riordan, Erik Theissen
This paper investigates the efficacy of low-frequency transactions-based liquidity measures to describe actual (high-frequency) liquidity. We show that the Corwin and Schultz (2012) and Abdi and Ranaldo (2017) estimators outperform other measures in describing time-series variations, irrespective of the observation frequency, trading venue, high-frequency liquidity benchmark, and cryptocurrency. Both measures perform well during high and low return, volatility and volume periods. The Kyle and Obizhaeva (2016) estimator and the Amihud (2002) illiquidity ratio outperform when estimating liquidity levels. These two estimators also reliably identify liquidity differences between trading venues. Overall, the results suggest that there is not yet a universally bestmeasure but there are reasonably good low-frequency measures.
This study examines the predictability of three major cryptocurrencies-bitcoin, ethereum, and litecoin-and the profitability of trading strategies devised upon machine learning techniques (e.g., linear models, random forests, and support vector machines). The models are validated in a period characterized by unprecedented turmoil and tested in a period of bear markets, allowing the assessment of whether the predictions are good even when the market direction changes between the validation and test periods. The classification and regression methods use attributes from trading and network activity for the period from August 15, 2015 to March 03, 2019, with the test sample beginning on April 13, 2018. For the test period, five out of 18 individual models have success rates of less than 50%. The trading strategies are built on model assembling. The ensemble assuming that five models produce identical signals (Ensemble 5) achieves the best performance for ethereum and litecoin, with annualized Sharpe ratios of 80.17% and 91.35% and annualized returns (after proportional round-trip trading costs of 0.5%) of 9.62% and 5.73%, respectively. These positive results support the claim that machine learning provides robust techniques for exploring the predictability of cryptocurrencies and for devising profitable trading strategies in these markets, even under adverse market conditions.
Teknolojinin gelişmesiyle birlikte son yıllarda küresel çağın sürekli ve değişen ihtiyaçlarına cevap verebilmek için her alanda olduğu gibi finans sektöründe de değişimler olmaktadır. Genel ve özel olarak çok fazla kripto para oluşturulmuştur. Örneğin Etherum, Bitcoin Cash, Ripple gibi kripto paralar ortaya çıkmıştır. Bunlardan en yaygın olanı ise Bitcoin'dir. Bu çerçevede popülerliği artarak hayatımızda yer alan kripto paraların finansal sisteme olan etkilerine değinilmektedir. Blok zinciri adını sıklıkla duyduğumuz kripto para madenciliği ve madencilerine de bu çalışmada yer verilmektedir. Özetle kripto paralar ve Bitcoin bu çerçevede ele alınacak ve incelenecektir. Bu tez çalışması kapsamında, BTC / USD döviz kuru, en yüksek işlem hacmi ve en değerli para birimleri ile EUR / USD, JPY / USD, XAU / UDS, CNY / USD, PETROL / USD pariteleri arasındaki ilişki Ocak 2017- Şubat 2021 dönemleri için Granger Nedensellik testi uygulanarak incelenmiştir. Analiz sonuçlarına göre EUR/USD, JPY/USD, XAU/USD paritesinden BTC/USD paritesine doğru tek yönlü bir nedenselliğin olduğu bulgusuna ulaşılmıştır. Diğer pariteler ile Bitcoin arasında nedensellik ilişkisi tespit edilememiştir.
Md. Jamal Hossain, Mohd Tahir Ismail, Mohammad Raquibul Hossain
This paper investigated the existence of structural break and impact of Gold and Platinum value on Bitcoin value. We also examined changes in the regime using three MSGARCH models, namely single-regime, two-regime, and three-regime, and compared their performances. We found the presence of break and significant impact of the Platinum value. Previous studies found that Gold has an impact on Bitcoin value, but empirically we could not find any. The two-regime MSGARCH model performs well among three models, and there is evidence of low volatility and high volatility regime. The out-of-sample forecast performance is almost same in the three models. In the long run, the presence of low volatility regime is more prominent than the high volatility regime.
This paper studies cryptocurrency. Firstly, this paper discusses the currency attribute of cryptocurrency. Secondly, this paper analyzes the advantages and disadvantages of cryptocurrency. Thirdly, this paper discusses the impact of cryptocurrency on the currency structure. Finally, this paper constructs the returns according to the daily price and statistically analyzes the yield difference of Bitcoin, Ethereum and Dogecoin. The ARIMA model is used to predict the return of cryptocurrency. This paper also gives the corresponding investment suggestions.
Deepak R Sawalka, Dhruvil S Saliya, Vatsal M Mehta, Atharva M Chiplunkar
Lately, Bitcoin is the most important in the digital currency market. Notwithstanding, costs of Bitcoin have exceptionally varied which make them undeniably challenging to foresee. Henceforth, this exploration plans to find the most proficient and most noteworthy precision model to foresee Bitcoin costs from different AI calculations. In this paper, we proposed to anticipate the Bitcoin cost precisely thinking about different boundaries that influence the Bitcoin esteem. By gathering data from various reference papers and applying progressively. The cycle occurs in the paper is first snapshot of the examination, we intend to comprehend and discover every day patterns in the Bitcoin market while acquiring understanding into ideal elements encompassing Bitcoin cost. Our informational collection comprises of different components identifying with the Bitcoin cost and installment network throughout consistently, recorded every day. By preprocessing the dataset, we apply the a few information mining strategies to diminish the commotion of information. Then, at that point the second snapshot of our examination, utilizing the accessible data, we will anticipate the indication of the every day value change with most elevated conceivable precision.