Ioannis Chalkiadakis, Anna Zaremba, Gareth W. Peters, Michael J. Chantler
This paper establishes a new framework for assessing multimodal statistical causality between cryptocurrency market (cryptomarket) sentiment and cryptocurrency price processes. In order to achieve this, we present an efficient algorithm for multimodal statistical causality analysis based on Multiple-Output Gaussian Processes. Signals from different information sources (modalities) are jointly modelled as a Multiple-Output Gaussian Process, and then using a novel approach to statistical causality based on Gaussian Processes (GPs), we study linear and non-linear causal effects between the different modalities. We demonstrate the effectiveness of our approach in a machine learning application by studying the relationship between cryptocurrency spot price dynamics and sentiment time-series data specific to the crypto sector, which we conjecture influences retail investor behaviour. The investor sentiment is extracted from cryptomarket news data via methods developed in the area of statistical machine learning known as Natural Language Processing (NLP). To capture sentiment, we present a novel framework for text to time-series embedding, which we then use to construct a sentiment index from publicly available news articles. We conduct a statistical analysis of our sentiment statistical index model and compare it to alternative state-of-the-art sentiment models popular in the NLP literature. In regard to the multimodal causality, the investor sentiment is our primary modality of exploration, in addition to price and a blockchain technology-related indicator (hash rate). Analysis shows that our approach is effective in modelling causal structures of variable degree of complexity between heterogeneous data sources and illustrates the impact that certain modelling choices for the different modalities can have on detecting causality. A solid understanding of these factors is necessary to gauge cryptocurrency adoption by retail investors and provide sentiment- and technology-based insights about the cryptocurrency market dynamics.
Jan 1, 2020·Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences
With the increase in the attention to cryptocurrency, studies on the factors affecting the price fluctuation of cryptocurrency have been actively conducted. Prior researches suggested that policy announcements (i.e., public information) related to cryptocurrency have been found to affect the price volatility in the market in particular. Privileged information, which is hard to be observable unlike public information published by the government or corporations, is hardly homogenously distributed to individual investors. However, it inevitably affects the price in any market. Therefore, this study aims to identify the information asymmetry, which is mainly formed by privileged information, in the cryptocurrency market. Moreover, this study examines whether investment sentiment, which mainly influences transaction behaviors of uninformed traders, has a significant effect on the cryptocurrency market as well. The results contribute to the understanding of the cryptocurrency market in a basis of the existing market theories.
Jan 1, 2020·Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences
With the rapid development of the Internet, cryptocurrencies have been gaining increasing amounts of attention dramatically. As a digital currency, it is not only used worldwide for online payments, but also traded as an investment tool on the market. Therefore, the ability to predict the price volatility will facilitate future investment and payment decisions. However, there are many uncertainties in the price movement of cryptocurrencies, and the prediction is extremely difficult. To this end, based on the transaction data of three different markets and the number and content of user comments and responses from online forums, this paper constructs a price prediction model of cryptocurrencies using a variety of machine learning and deep learning algorithms. It turns out that the trading price premium rate in different markets will affect the price to be predicted, and adding social media comment features can significantly improve the accuracy of the forecast. This article is conducive to investors who encrypt currencies to make more scientific decisions.
Yuze Li, Shangrong Jiang, Xuerong Li, Shouyang Wang
Abstract In recent years, Bitcoin has received substantial attention as potentially high-earning investment. However, its volatile price movement exhibits great financial risks. Therefore, how to accurately predict and capture changing trends in the Bitcoin market is of substantial importance to investors and policy makers. However, empirical works in the Bitcoin forecasting and trading support systems are at an early stage. To fill this void, this study proposes a novel data decomposition-based hybrid bidirectional deep-learning model in forecasting the daily price change in the Bitcoin market and conducting algorithmic trading on the market. Two primary steps are involved in our methodology framework, namely, data decomposition for inner factors extraction and bidirectional deep learning for forecasting the Bitcoin price. Results demonstrate that the proposed model outperforms other benchmark models, including econometric models, machine-learning models, and deep-learning models. Furthermore, the proposed model achieved higher investment returns than all benchmark models and the buy-and-hold strategy in a trading simulation. The robustness of the model is verified through multiple forecasting periods and testing intervals.
Bitcoin is a current popular cryptocurrency with a promising future. It’s like a stock market with time series, the series of indexed data points. We looked at different deep learning networks and methods of improving the accuracy, including min-max normalization, Adam optimizer and windows min-max normalization. We gathered data on the Bitcoin price per minute, and we rearranged them to reflect Bitcoin price in hours, a total of 56,832 points. We took 24 hours of data as input and output the Bitcoin price of the next hour. We compared the different models and found that the lack of memory means that Multi-Layer Perceptron (MLP) is ill-suited for the case of predicting price based on current trend. Long Short-Term Memory (LSTM) provides relatively the best prediction when past memory and Gated Recurrent Network (GRU) is included in the model.
The goal of this paper is to compare the accuracy of bitcoin price in USD prediction based on two different model, Long Short term Memory (LSTM) network and ARIMA model. Real-time price data is collected by Pycurl from Bitfine. LSTM model is implemented by Keras and TensorFlow. ARIMA model used in this paper is mainly to present a classical comparison of time series forecasting, as expected, it could make efficient prediction limited in short-time interval, and the outcome depends on the time period. The LSTM could reach a better performance, with extra, indispensable time for model training, especially via CPU.
This paper explores the symmetric and asymmetric dependency structure of decomposed return series of Gold and eight cryptocurrencies to establish the hedging and diversification potentials of these asset classes. Daily data spanning 30 April 2013 to 18 April 2019 are employed within the Ensemble Empirical Mode Decomposition and Quantile-in-Quantile regression techniques. Our empirical results provide evidence that cryptocurrencies and Gold can both hedge and diversify for each other at different conditional distributions of their returns. We also find that cryptocurrencies are not purely speculative but can be driven by medium- and long-term fundamentals. In addition, both Gold and cryptocurrencies can be hedge and diversifiers for other traditional asset classes such as crude oil, fiat currencies, and other commodities.
In this article we forecast daily closing price series of Bitcoin, Litecoin and Ethereum cryptocurrencies, using data on prices and volumes of prior days. Cryptocurrencies price behaviour is still largely unexplored, presenting new opportunities for researchers and economists to highlight similarities and differences with standard financial prices. We compared our results with various benchmarks: one recent work on Bitcoin prices forecasting that follows different approaches, a well-known paper that uses Intel, National Bank shares and Microsoft daily NASDAQ closing prices spanning a 3-year interval and another, more recent paper which gives quantitative results on stock market index predictions. We followed different approaches in parallel, implementing both statistical techniques and machine learning algorithms: the Simple Linear Regression (SLR) model for uni-variate series forecast using only closing prices, and the Multiple Linear Regression (MLR) model for multivariate series using both price and volume data. We used two artificial neural networks as well: Multilayer Perceptron (MLP) and Long short-term memory (LSTM). While the entire time series resulted to be indistinguishable from a random walk, the partitioning of datasets into shorter sequences, representing different price "regimes", allows to obtain precise forecast as evaluated in terms of Mean Absolute Percentage Error(MAPE) and relative Root Mean Square Error (relativeRMSE). In this case the best results are obtained using more than one previous price, thus confirming the existence of time regimes different from random walks. Our models perform well also in terms of time complexity, and provide overall results better than those obtained in the benchmark studies, improving the state-of-the-art.
Cryptocurrencies, such as Bitcoin, are one of the most controversial and complex technological innovations in today's financial system. This study aims to forecast the movements of Bitcoin prices at a high degree of accuracy. To this aim, four different Machine Learning (ML) algorithms are applied, namely, the Support Vector Machines (<i>SVM</i>), the Artificial Neural Network (<i>ANN</i>), the Naï ve Bayes (<i>NB)</i> and the Random Forest (<i>RF</i>) besides the logistic regression (LR) as a benchmark model. In order to test these algorithms, besides existing continuous dataset, discrete dataset was also created and used. For the evaluations of algorithm performances, the <i>F</i> statistic, accuracy statistic, the Mean Absolute Error (MAE), the Root Mean Square Error (RMSE) and the Root Absolute Error (RAE) metrics were used. The <i>t</i> test was used to compare the performances of the SVM, ANN, NB and RF with the performance of the LR. Empirical findings reveal that, while the <i>RF</i> has the highest forecasting performance in the continuous dataset, the <i>NB</i> has the lowest. On the other hand, while the <i>ANN</i> has the highest and the <i>NB</i> the lowest performance in the discrete dataset. Furthermore, the discrete dataset improves the overall forecasting performance in all algorithms (models) estimated.
Decentralized cryptocurrencies have gained a lot of attention over the last decade. Bitcoin was introduced as the first cryptocurrency to allow direct online payments without relying on centralized financial entities. The use of Bitcoin has vastly grown as a financial asset rather than just a tool for online payments. A lot of cryptocurrencies have been created since 2011 with Bitcoin dominating the cryptocurrencies' market. With plenty of cryptocurrencies being used as financial assets and with millions of trades being executed through different exchange services, cryptocurrencies are susceptible to trading problems and challenges similar to those traditionally encountered in the financial domain. Price and trend prediction, volatility prediction, portfolio construction and fraud detection are some examples related to trading. In addition, there are other challenges that are specific to the domain of cryptocurrencies such as mining, cybersecurity, anonymity and privacy. In this paper, we survey the application of artificial intelligence techniques to address these challenges for cryptocurrencies with their vast amount of daily transactions, trades and news that are beyond human capabilities to analyze and learn from. This paper discusses the recent research work done in this emerging area and compares them in terms of used techniques and datasets. It also highlights possible research gaps and some potential areas for improvement.
Over the past few years, with the advent of blockchain technology, there has been a massive increase in the usage of Cryptocurrencies. However, Cryptocurrencies are not seen as an investment opportunity due to the market's erratic behavior and high price volatility. Most of the solutions reported in the literature for price forecasting of Cryptocurrencies may not be applicable for real-time price prediction due to their deterministic nature. Motivated by the aforementioned issues, we propose a stochastic neural network model for Cryptocurrency price prediction. The proposed approach is based on the random walk theory, which is widely used in financial markets for modeling stock prices. The proposed model induces layer-wise randomness into the observed feature activations of neural networks to simulate market volatility. Moreover, a technique to learn the pattern of the reaction of the market is also included in the prediction model. We trained the Multi-Layer Perceptron (MLP) and Long Short-Term Memory (LSTM) models for Bitcoin, Ethereum, and Litecoin. The results show that the proposed model is superior in comparison to the deterministic models.
Bitcoin is considered to be most valuable and expensive currency in the world. Besides being first decentralized digital currency, its value has also experienced a steep increase, from around 1 dollar in 2010 to around 18000 in 2017. In recent years, it has attracted considerable attention in a diverse set of fields, including economics, finance and computer science. In economics, the primary focus has always been on studying how it affects the market, determining reasons behinds its price fluctuations, and predicting its future prices. In computer science, the focus is on its vulnerabilities, scalability, and other techno-cryptoeconomic issues. Firstly, we are going to collect the historical data of Bitcoin prices over the years 2013 to 2019 and do prediction for the year 2020. We have aimed to justify the usefulness of traditional Autoregressive Integrative Moving Average (ARIMA) model for predicting bitcoin prices. We have predicted the closing price of bitcoin for first seven days of January 2020. Further, we have created web services using ASP.NET to make the predictions on bitcoin price online and lastly, we have plotted the results in a responsive chart using Highcharts.
Günümüzde kripto para birimlerinin önemi gittikçe artmaktadır. Kripto para birimleri sanal oyun platformlarında kullanılırken, şu an pek çok kurum ve kuruluş tarafından ödeme aracı olarak kullanılmaktadır. Güvenlik risklerine karşı blockchain (Blok Zinciri) adı verilen algoritması ile üretimi sağlanmaktadır. Kripto para fiyatlarının doğru olarak tahmin edilmesi yatırımcı ve karar vericiler açısından büyük önem taşımaktadır. Bu çalışma kapsamında en çok kullanılan dört kripto para birimine (Bitcoin, Ethereum, Ripple, Litecoin) ait fiyat değerleri tahmin edilmiştir. Çoklu kırılma testinden yararlanılarak her seriye ait kırılmalar belirlenerek analiz genişletilmiştir. Ele alınan sanal para değerlerini doğru bir şekilde tahmin etmek amacıyla hem klasik zaman serisi modellerinden hem de üç farklı tür yapay sinir ağı modelinden faydalanılmıştır. Ayrıca elde edilen tahminler üzerinde basit birleştirilme teknikleri uygulanmıştır. Rassal yürüyüşün egemen olduğu bu seriler arasından, özellikle işlem hacmi ve bilinilirliği en fazla olan Bitcoin sanal parasında rassal yürüyüş modelinden daha iyi sonuçlar elde edildiği gözlemlenmiştir.
In this study, the relationship between the popularity of cryptocurrencies and their price, return and trading volumes are examined through time series analysis. The popularity variable is determined according the frequency of cryptocurrencies being searched on the internet. Stationarity of series is examined by Vogelsang and Perron (1998) structural breaks ADF unit root test. According to the test results, all series are found to be stationary at level values. VAR analyses and impulse-response functions are performed to reveal dynamic interaction between the series. According to impulse - response test results, returns of BITCOIN decreased against a decreasing shock in the number searches on the internet and its price and trading volume followed a fluctuating course. In order to see the causality relationship between variables the Granger causality test is conducted. Regression analyses are performed using ordinary least squares (OLS) method through three different equations. According to the result of the regression analysis, an increase in the number of internet searches for cryptocurrencies was found to positively affect prices, returns and trading volumes of all cryptocurrencies. The highest impact on prices and trading volume is observed in BITCOIN, while the highest effect on returns is observed in LITECOIN. According to the findings, popularity can be considered an important determinant for price, returns and trading volumes of cryptocurrencies.
Bu çalışma, Bitcoin’in fiyat davranışını otoregresif birim kökü olan iki rejimli bir TAR modeli kullanarak araştırmaktadır. Çalışmada, durağan dışılığı ve doğrusal olmamayı eş zamanlı olarak sınayan Caner ve Hansen (2001) tarafından geliştirilen yöntem kullanılmıştır. Bu amaçla, 16.07.2010 – 27.11.2018 dönemi için (3.056 adet günlük gözlem) Bitcoin kapanış fiyatlarına ait veri seti oluşturularak Bitcoin fiyatlarının etkin olup olmadığı incelenmiştir. Elde edilen bulgular, Bitcoin fiyatlarının tüm dönem dikkate alındığında zayıf formda etkin piyasalar hipotezini desteklemektedir. Ancak rejimler arası geçiş dikkate alındığında Bitcoin fiyat serisinde iki rejim olduğu sonucuna ulaşılmıştır. Birinci rejimde zayıf forma etkin piyasalar hipotezinin geçerli olduğu, ancak ikinci rejimde geçerli olmadığı tespit edilmiştir.
The aim of this study is to develop forecasting cryptocurrency price movement using moving average. The cryptocurreny that selected in this study is Bitcoin Cash. The observation periods involved in this
Ángeles López Cabarcos, Ada M. Pérez-Pico, Juan Piñeiro Chousa, Aleksandar Šević
Bitcoin is the cryptocurrency with the largest market capitalization, and many studies have examined its role in financial markets. In this manuscript, we contribute to the extant body of knowledge by analyzing the Bitcoin behavior and the effect that investor sentiment, S&P 500 returns, and VIX returns have on Bitcoin volatility using GARCH and EGARCH models. The results suggest that Bitcoin volatility is more unstable in speculative periods. In stable periods, S&P 500 returns, VIX returns, and sentiment influence Bitcoin volatility.
İnternet kullanımındaki hızlı gelişmeler ile birlikte, insan hayatına fiziksel olarak dahil olan para da dijitalleşmeye başlamıştır. Bu tür dijitalleşmiş para birimlerine genel olarak kripto para denilmektedir. Hali hazırda, Bitcoin, kripto para birimleri arasında en yüksek işlem hacmine sahiptir. İlk Bitcoin 2009 yılında piyasaya sürüldü. Fakat son birkaç yılda ciddi derecede ilgi çekmeye başladı. Bu ilginin temel nedenlerinden birisi, Bitcoin'in değerinde önemli artışların olmasıdır. Söz konusu değer artışları bağlamında, Bitcoin piyasasında spekülatif balonların varlığının araştırılması önem arz etmektedir. Bu bağlamda, çalışmanın amacı 2015-2018 dönemi boyunca Bitcoin piyasasında spekülatif balonların varlığını araştırmaktır. Amaç doğrultusunda, spekülatif balonların tespiti için Phillips vd. (2015) tarafından geliştirilen Genelleştirilmiş Eküs ADF testi kullanılmıştır. Elde edilen bulgular, Bitcoin piyasasında çok sayıda baloncuk olduğunu göstermektedir.
Cryptocurrencies, such as Bitcoin, are becoming increasingly popular, having been widely used as an exchange medium in areas such as financial transaction and asset transfer verification. However, there has been a lack of solutions that can support real-time price prediction to cope with high currency volatility, handle massive heterogeneous data volumes, including social media sentiments, while supporting fault tolerance and persistence in real time, and provide real-time adaptation of learning algorithms to cope with new price and sentiment data. In this paper we introduce KryptoOracle, a novel real-time and adaptive cryptocurrency price prediction platform based on Twitter sentiments. The integrative and modular platform is based on (i) a Spark-based architecture which handles the large volume of incoming data in a persistent and fault tolerant way; (ii) an approach that supports sentiment analysis which can respond to large amounts of natural language processing queries in real time; and (iii) a predictive method grounded on online learning in which a model adapts its weights to cope with new prices and sentiments. Besides providing an architectural design, the paper also describes the KryptoOracle platform implementation and experimental evaluation. Overall, the proposed platform can help accelerate decision-making, uncover new opportunities and provide more timely insights based on the available and ever-larger financial data volume and variety.
This study aims to evaluate the effect of adding bitcoin in a diversified portfolio comprising traditional assets (bonds, European, Asian and international stock market indices) and alternative assets (gold and commodities) from an European investor point of view. Monthly data cover the period from August 2010 to March 2016. This period is divided into two sub-periods during the euro zone debt crisis and after the crisis. To do this, we will, first of all, apply the genetic algorithms method to optimize two types of portfolio with and without bitcoin for both subperiods. Next, we will compare the two optimal portfolios using the stochastic dominance approach during the two sub-periods. Genetic algorithms show that the weighting of bitcoin during the crisis is greater than that after the crisis, which proves that bitcoin has a safe haven value during unstable periods. The results of stochastic dominance show that during and after the crisis, the portfolio including bitcoin dominates the one without bitcoin according to the 2nd and 3rd order. This shows that risk-averse investors prefer to include bitcoin in their portfolios to maximize their expected utility.