Kalpanasonika R, Sayasri S M, Vinothini A, Suga Priya H
The accusative of this paper is to predict the bitcoin price accurately by taking various parameters into consideration which affects the bitcoin value. Here multi-layer perceptron algorithms under deep learning are used to predict the price of crypto-currency. Many researchers have analysed the crypto-currency features in many ways such as, market price prediction, the impact of cryptocurrency in real life. It has the ability to make long-term prediction of the exchange price in crypto-currencies particularly in US dollar, based on historical trends. The bitcoin cost prediction is done based on the data set which consists of 13 features relating to the crypto-currency price recorded daily over the period of particular range.
This paper fits in the trend of discussing the efficiency of cryptocurrency markets. Since 2008, when Bitcoin appeared on the market, arbitrageurs from all over the world have been trying to find the gaps in the markets, which will let them earn risk-free money using financial operations. Although a lot of researchers are trying to figure out arbitrage opportunities, looking at different exchanges and using different cryptocurrencies, so far hardly anyone has looked at arbitrage opportunities with the use of FIAT currencies within the same or different exchanges. This paper examines such opportunities for three different exchanges, i.e. Kraken, Bitfinex and Bitstamp -exchanges that enable trading in USD and EUR against Bitcoin at the same time. The main empirical results suggest that there are significant arbitrage opportunities on these markets. In the paper, we also show the main constraints in FIAT currencies arbitrage on cryptocurrency exchanges.
Cryptocurrency is playing an increasingly important role in reshaping the financial system due to its growing popular appeal and mechant acceptance. While many people are making investments in Cryptocurrency, the dynamical features, uncertainty, the predictability of Cryptocurrency are still mostly unknown, which dramatically risk the investments. It is a matter to try to understand the factors that infiuence the value formation. In this study, we use advanced artificial intelligence frameworks of fully connected Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) Recurrent Neural Network to analyse the price dynamics of Bitcoin, Etherum, and Ripple. We find that ANN tends to rely more on long-term history while LSTM tends to rely more on short-term dynamics, which indicate the efficiency of LSTM to utilise useful information hidden in historical memory is stronger than ANN. However, given enough historical information ANN can achieve a similar accuracy, compared with LSTM. This study provides a unique demonstration that Cryptocurrency market price is predictable. However, the explanation of the predictability could vary depending on the nature of the involved machine-learning model.
Avinash Barnwal, Hari Pad Bharti, Aasim Ali, Vishal Krishna Singh
Predicting the direction of assets have been an active area of study and a difficult task. Machine learning models have been used to build robust models to model the above task. Ensemble methods is one of them showing results better than a single supervised method. In this paper, we have used generative and discriminative classifiers to create the stack, particularly 3 generative and 6 discriminative classifiers and optimized over one-layer Neural Network to model the direction of price cryptocurrencies. Features used are technical indicators used are not limited to trend, momentum, volume, volatility indicators, and sentiment analysis has also been used to gain useful insight combined with the above features. For Cross-validation, Purged Walk forward cross-validation has been used. In terms of accuracy, we have done a comparative analysis of the performance of Ensemble method with Stacking and Ensemble method with blending. We have also developed a methodology for combined features importance for the stacked model. Important indicators are also identified based on feature importance.
Thomas Fischer, Christopher Krauß, Alexander Deinert
Machine learning research has gained momentum—also in finance. Consequently, initial machine-learning-based statistical arbitrage strategies have emerged in the U.S. equities markets in the academic literature, see e.g., Takeuchi and Lee (2013); Moritz and Zimmermann (2014); Krauss et al. (2017). With our paper, we pose the question how such a statistical arbitrage approach would fare in the cryptocurrency space on minute-binned data. Specifically, we train a random forest on lagged returns of 40 cryptocurrency coins, with the objective to predict whether a coin outperforms the cross-sectional median of all 40 coins over the subsequent 120 min. We buy the coins with the top-3 predictions and short-sell the coins with the flop-3 predictions, only to reverse the positions after 120 min. During the out-of-sample period of our backtest, ranging from 18 June 2018 to 17 September 2018, and after more than 100,000 trades, we find statistically and economically significant returns of 7.1 bps per day, after transaction costs of 15 bps per half-turn. While this finding poses a challenge to the semi-strong from of market efficiency, we critically discuss it in light of limits to arbitrage, focusing on total volume constraints of the presented intraday-strategy.
Mike Cudd, Kristen Ritterbush, Marcelo Eduardo, Chris Smith
One of the most significant innovations in the world of finance has been the creation and evolvement of cryptocurrencies. These digital means of exchange have been the focus of extensive news coverage, especially the Bitcoin, with a primary focus on the tremendous potential return and the high level of accompanying risk. In this chapter, we examine the risk-return pattern for an array of cryptocurrencies, contrasting the pattern with those of conventional currency and equity investments. We find the measures of cryptocurrency returns and risk to be a very high multiple of those of conventional investments, and the pattern is determined to be robust relative to the time frame. Consequently, cryptocurrencies are determined to provide an alternative to investors that involves tremendously high risk and return.
The goal of this chapter is to present recent developments about Bitcoin1 price modeling and related applications. Precisely, we consider a bivariate model in continuous time to describe the behavior of Bitcoin price and of the investors’ attention on the overall network. The attention index affects Bitcoin price through a suitable dependence on the drift and diffusion coefficients and a possible correlation between the sources of randomness represented by the driving Brownian motions. The model is fitted on historical data of Bitcoin prices, by considering the total trading volume and the Google Search Volume Index as proxies for the attention measure. Moreover, a closed formula is computed for European-style derivatives on Bitcoin. Finally, we discuss two possible extensions of the model. Precisely, we investigate the relation between the correlation parameter and possible bubble effects in the asset price; further, we consider a multivariate framework to represent the special feature of Bitcoin being traded on several exchanges and we discuss conditions to rule out arbitrage opportunities in this setting.
Matthias Schnaubelt, Jonas Rende, Christopher Krauß
The majority of electronic markets worldwide employ limit order books, and the recently emerging exchanges for cryptocurrencies pose no exception. With this work, we empirically analyze whether commonly observed empirical properties from established limit order exchanges transfer to the cryptocurrency domain. Based on the literature, we establish a structured methodological framework to conduct analyses in a systematic and comprehensive way. We then present results from a unique and extensive limit order data set acquired from major cryptocurrency exchanges for the currency pair Bitcoin to US Dollar. We recover many observations from mature markets, such as a symmetry between the average ask and the average bid side of the order book, autocorrelation in returns on the smallest time scales only, volatility clustering and the timing of large trades. We also observe some idiosyncrasies: The distributions of trade size and limit order prices deviate from commonly observed patterns. Also, we find limit order books to be relatively shallow and liquidity costs to be relatively high when compared to established markets.
Matheus José Silva de Souza, Fahad Almudhaf, Bruno Miranda Henrique, Ana Beatriz Silveira Negredo · 7 authors
This paper aims to investigate how Machine Learning (ML) techniques perform in the prediction of cryptocurrency prices. We answer if Support Vector Machines (SVM) and Artificial Neural Networks (ANN) based strategies can generate abnormal risk-adjusted returns when applied to Bitcoin, the largest decentralized digital currency in terms of market capitalization. Findings indicate that traders are able to earn conservative returns on the risk adjusted basis, even accounting for transaction costs, when using SVM. Furthermore, the study suggests that ANN can explore short run informational inefficiencies to generate abnormal profits, being able to beat even buy-and-hold during strong bull trends.
Abstract Using extreme value analysis, we investigate the tail risk behavior of the high‐frequency (hourly) log returns of four most popular cryptocurrencies. The analysis is conducted on high‐frequency returns data, estimating value at risk and expected shortfall with varying thresholds. We find that Ripple is the most risky cryptocurrency exhibiting the largest potential gain or loss for both positive and negative (hourly) log returns at every percentile and threshold. Bitcoin is the least risky cryptocurrency.
Recent research on the economics of digitization investigates the dramatic changes in markets by digital technology. Digital technology has caused significant differences in in the cost of storage, computation, and transmission of data. As one of the latest sign of digitization in our life, the use of cryptocurrencies has been drawing attention of all market players. Blockchain technology is recently reallocating resources, restructuring of routines, changing market relationships and patterns of the flow of goods and services. This study investigates the coherence of Bitcoin with the movements of the main indicators of different markets. Aim of this research is to clarify whether this cryptocurrency follows the market conditions or not. Because the movements of the market values of Bitcoin are aimed to be investigated to show that they can be used separately as a tool of risk management. For this reason, wavelet analysis has been employed to define cross-correlation between time series of the daily USD value of Bitcoin and some market indicators. Some literature asserts that Bitcoin has recently started to follow market conditions. If Bitcoin process follows the market conditions more than before, that if This analysis will explain if there is a change in hedging possibility of Bitcoin recently.
In this study, we investigate the relationship between Bitcoin mining technology variables and Bitcoin returns, using a GARCH-M model. Additionally, we examine the predictive power of the mining technology variables on future Bitcoin returns. We find that mining difficulty and block size are inversely related to Bitcoin returns. Additionally, our findings signifying that the higher the block size the lower the Bitcoin price and consequently the lower the expected return. Second, our findings show that mining difficulty and block size are robust predictors of future Bitcoin returns.
Daniel Traian Pele, Miruna Mazurencu-Marinescu-Pele
In this paper we investigate the ability of several econometrical models to forecast value at risk for a sample of daily time series of cryptocurrency returns. Using high frequency data for Bitcoin, we estimate the entropy of intraday distribution of logreturns through the symbolic time series analysis (STSA), producing low-resolution data from high-resolution data. Our results show that entropy has a strong explanatory power for the quantiles of the distribution of the daily returns. Based on Christoffersen's tests for Value at Risk (VaR) backtesting, we can conclude that the VaR forecast build upon the entropy of intraday returns is the best, compared to the forecasts provided by the classical GARCH models.
Muhammad Ali Nasir, Toan Luu Duc Huynh, Sang Phu Nguyen, Duy Duong
In the context of the debate on the role of cryptocurrencies in the economy as well as their dynamics and forecasting, this brief study analyzes the predictability of Bitcoin volume and returns using Google search values. We employed a rich set of established empirical approaches, including a VAR framework, a copulas approach, and non-parametric drawings, to capture a dependence structure. Using a weekly dataset from 2013 to 2017, our key results suggest that the frequency of Google searches leads to positive returns and a surge in Bitcoin trading volume. Shocks to search values have a positive effect, which persisted for at least a week. Our findings contribute to the debate on cryptocurrencies/Bitcoins and have profound implications in terms of understanding their dynamics, which are of special interest to investors and economic policymakers.
Bitcoin is a tremendously debated phenomenon in the world of finance and in recent the scientific literature on the topic has expanded. In this thesis,the bitcoin to US dollar exchange rate is examined through various conditional variance models to describe its highly volatile nature. We examine whether the introduction of bitcoin futurescontractsin late 2017 has had a decreasing impact on price volatility by estimatingthe unconditional variance. The log-return of the bitcoin exchange rate is analysed,and there is evidence of volatility clustering and time-varying volatility. Consequently, the variance is modelled through the GARCH(1,1), EGARCH(1,1) and GJR-GARCH(1,1) modelswith innovations followingthree distributions. The in-sample selection method selectedthe EGARCH(1,1) model where innovation terms follow a generalizederror distribution as the most parsimonious model. The findings show that volatilityhas not decreased after the introduction of bitcoin futures on regulated exchanges. \nKeywords: Bitcoin, conditional variancemodelling, bitcoin futures, price volatility exchange rate, statistical analysis
Zuzana Rakovská – Masaryk University, Faculty of Economics and Administration, Lipova 41a, 602 00 Brno, Czech Republic DOI: https://doi.org/10.31410/ITEMA.2019.241 3rd International Scientific Conference on Recent Advances in Information Technology, Tourism, Economics, Management and Agriculture – ITEMA 2019 – Bratislava, Slovakia, October 24, 2019, CONFERENCE PROCEEDINGS published by the Association of Economists and Managers […]
Bitcoin has emerged to become the most popular cryptocurrency and its presence\nhas the potential to disrupt existing payment and monetary systems. Over the past\ndecade, the bitcoin price has exhibited extreme volatility, puzzling for both academics\nand market practitioners. We examine the dynamic relationship between\ninvestor attention and the bitcoin price using principal component analysis and vector\nerror correction models and discover that investor attention is an important contributor\nin bitcoin price formation. Variance decomposition analysis suggests that\ninvestor attention explain a significant amount of future variations in the bitcoin\nprice, and investor attention can be used to predict direction of future price change.\nOur study offers insight into the bitcoin market and the economic impact of investor\nattention.
The purpose of this thesis is to learn if it’s possible to gain higher risk-adjusted profits than buy-and-hold -strategy on intraday bitcoin markets using moving averages or trading range breakout. Data used is price notations of bitcoin with 1-minute interval from 2017 to 2019. \n \nThere were many strategies that statistically significantly outperformed buy-and-hold -strategy even when trading fees were reduced. Different methods such as stop-loss and bands were able to significantly reduce volatility of returns. However, same trading rules don’t work well in different market conditions. Results from the train-set and test-set differed largely and were therefore not valid. Also, none of the strategies were able to outperform CCi30 cryptocurrency index when fees were reduced. \n \nTherefore, while some support was found to conclude that outperforming the index is possible, more data and research would be needed to validate these results.