In this study, we study the price dynamics of cryptocurrencies using adaptive complementary ensemble empirical mode decomposition (ACE-EMD) and Hilbert spectral analysis. This is a multiscale noise-assisted approach that decomposes any time series into a number of intrinsic mode functions, along with the corresponding instantaneous amplitudes and instantaneous frequencies. The decomposition is adaptive to the time-varying volatility of each cryptocurrency price evolution. Different combinations of modes allow us to reconstruct the time series using components of different timescales. We then apply Hilbert spectral analysis to define and compute the instantaneous energy-frequency spectrum of each cryptocurrency to illustrate the properties of various timescales embedded in the original time series.
To protect against risks arising from fluctuations in spot prices and better manage risk, investors might evaluate futures markets. The role of price discovery in the futures markets and the possibility of reducing certain risks increase the importance of researching the relationship between spot and futures prices. This study aims to determine whether there is a relationship between the Bitcoin spot prices and the Bitcoin futures prices. To this end, the relationship between the two markets is analyzed using Johansen Cointegration analysis and Vector Error Correction Model (VECM) using the daily data of the period 02.23.2017 – 08.31.2021. Unit root tests show that each series are not stationary at the level values and that the first differences of the series are stationary. The results of the cointegration analysis show that there is a long-term equilibrium relationship between the bitcoin spot market and the bitcoin futures market, and it is a single cointegration vector. The Granger causality test based on the vector error correction model was used to determine the causality relationship between the series. It has been determined that there is a unidirectional causality relationship from the Bitcoin spot market to the Bitcoin futures market. Bitcoin is a new financial tool that attracts the attention of investors. Investors make transactions on Bitcoin for speculative purposes. Therefore, unlike other investment instruments, spot prices in the bitcoin market affect futures prices.
AI and data driven solutions have been applied to different fields and achieved outperforming and promising results. In this research work we apply k-Nearest Neighbours, eXtreme Gradient Boosting and Random Forest classifiers for detecting the trend problem of three cryptocurrency markets. We use these classifiers to design a strategy to trade in those markets. Our input data in the experiments include price data with and without technical indicators in separate tests to see the effect of using them. Our test results on unseen data are very promising and show a great potential for this approach in helping investors with an expert system to exploit the market and gain profit. Our highest profit factor for an unseen 66 day span is 1.60. We also discuss limitations of these approaches and their potential impact on Efficient Market Hypothesis.
This study tested the efficient-market hypothesis (EMH) to examine information efficacy in the cryptocurrency market. We conducted three random walk tests to verify the weak-form EMH and used the event study method to test the semi-strong-form EMH. The analysis results demonstrated that 54 (6.04%) of the total of 893 cryptocurrency units satisfied the weak-form EMH, and 24 (2.695%) met the semi-strong market hypothesis. Furthermore, we found that, among the cryptocurrency exchanges that were established before November 2017, large size exchanges were more likely to satisfy the weak- and semi-strong-form EMHs.
Yash Wadalkar, Yellamraju V H Sai Tarun, Jaiesh Singhal, Reena Sonkusare
Bitcoin, one of the most famous and high-in- demand cryptocurrencies, is a type of digital asset that is extremely difficult to track and make predictions upon. In addition, Bitcoin price does not correlate with market- movements, therefore, predicting its price action and its locus is an ordeal. In this paper, we have followed a comparative analysis approach, wherein we are using four different models to predict the trend of BTC Time series data. The results justify that the models have achieved accurate forecasting trends. During the period of 16th to 31st December 2020, Bitcoin prices experienced considerably high swings, due to the increased demand for it. In quantitative terms, the prices experienced fluctuations to the tune of 8000 USD. Despite these enormous price changes, we were able to achieve a model, that helped us attain a Mean Absolute Error (MAE) of 153.55 USD and Mean Square Error (MSE) of 43231.80 USD. Conventional Bitcoin price predicting researches follow a single to two model approach. However, for a highly volatile asset like Bitcoin, making long-term predictions and generalizing them based on limited number of models results in low accuracy outputs. This gap has been bridged in our research, we have worked with different models, as well as fragmented the time intervals into smaller portions, post which the prediction was made for only 2 days. Using this approach, we attained results with least error rates. The results obtained clearly show that ARIMA is the best model for predicting the future trends for BTC time series data. It takes into account the different types of decompositions like Regular Trend, Sessional and Residual Trend making the model give the best results.
This dissertation contributes to the growing body of research on cryptocurrencies by addressing their economic, behavioral, and financial dimensions through a series of empirical essays. The studies collectively examine the determinants of cryptocurrency pricing, the role of investor sentiment and political uncertainty, and the implications of advanced portfolio optimization techniques—including machine learning approaches—for cryptocurrency investment management. The findings offer new insights into how digital assets behave as alternative investments, how they respond to external shocks, and how quantitative methods can be used to enhance portfolio performance in this highly volatile and evolving market. The first essay, Do FEARS Drive Bitcoin?, explores the relationship between investor sentiment and Bitcoin returns using a novel sentiment index derived from financial and media-based fear measures (FEARS). Employing econometric time-series models, the study finds that heightened investor fear significantly predicts short-term increases in Bitcoin trading volumes and volatility, consistent with Bitcoin’s perception as both a speculative and hedging instrument. However, the analysis also reveals asymmetric effects: while fear-driven demand raises short-term prices, sustained pessimism weakens long-term valuation. Robustness tests confirm the persistence of sentiment effects across multiple proxies and subperiods, demonstrating that behavioral factors remain central to cryptocurrency price formation. The second essay, Risk-Based Portfolio Optimization for Cryptocurrencies, examines how traditional risk-based allocation frameworks—such as minimum variance, equal risk contribution, and risk parity—perform in a cryptocurrency context characterized by extreme returns and tail dependencies. Using a dataset of major digital assets, the analysis compares the performance of various optimization strategies under different market regimes. The findings reveal that while risk parity strategies deliver superior diversification benefits, they remain vulnerable to extreme downside risk. Incorporating tail-risk measures and conditional performance adjustments substantially improves risk-adjusted returns, emphasizing the need for adaptive and non-normal risk frameworks in digital asset management. The third essay, Bitcoin and Global Political Uncertainty – Evidence from the U.S. Election Cycle, investigates Bitcoin’s role as a hedge or safe haven during periods of heightened political uncertainty. Using event-study and regression approaches, the results show that Bitcoin exhibits strong hedging characteristics during politically volatile periods, particularly around U.S. election cycles. However, its behavior varies asymmetrically with the type of uncertainty—economic versus institutional—highlighting that Bitcoin’s hedging function is conditional rather than universal. The fourth essay, Cryptocurrencies and the Low Volatility Anomaly, tests whether the well-documented low-volatility anomaly in equity markets extends to the cryptocurrency universe. Using portfolio sorting and cross-sectional regression analyses, the study finds that low-volatility cryptocurrencies outperform their high-volatility counterparts on a risk-adjusted basis, even after accounting for liquidity and size effects. This evidence challenges the perception of cryptocurrencies as uniformly speculative assets and suggests that market inefficiencies and behavioral biases may sustain persistent return anomalies in digital asset markets. The final essay, Beyond Risk Parity – A Machine Learning-Based Hierarchical Risk Parity Approach on Cryptocurrencies, proposes a novel portfolio optimization framework that integrates machine learning techniques with hierarchical clustering methods. By capturing complex non-linear relationships between assets, the hierarchical risk parity (HRP) approach outperforms traditional covariance-based methods in terms of diversification, turnover reduction, and out-of-sample stability. Empirical tests confirm that the machine learning-enhanced HRP model achieves higher Sharpe ratios and lower drawdowns across multiple rebalancing frequencies, demonstrating its robustness for high-dimensional and noisy cryptocurrency data. Collectively, the essays provide a comprehensive and multi-faceted understanding of the cryptocurrency market from both behavioral and quantitative perspectives. They highlight the dual nature of digital assets—as speculative vehicles sensitive to sentiment and uncertainty, and as emerging investment instruments that can be systematically managed through advanced quantitative techniques. The dissertation advances academic discussions on asset pricing, risk management, and market efficiency in the context of decentralized finance, while offering practical insights for institutional investors navigating the challenges and opportunities of the rapidly evolving digital asset ecosystem.
Over the last years, cryptocurrencies have gained popularity as a means of exchange, but mostly as an investment asset that can yield important earnings. Accurate cryptocurrency price prediction is the holy grail of investors, yet the task is extremely complex and tedious since cryptocurrencies exhibit high volatility and steep fluctuations compared to fiat money, while they depend on a plethora of factors related to the blockchain network, market trends, social popularity and the prices of other (crypto)currencies. Thus, simple statistical methods are not able to capture the complexity of cryptocurrency exchange rate, forcing researchers to turn to advanced machine learning techniques. In this work, we present a methodology for building deep learning models to forecast the price of cryptocurrencies and apply it to the prediction of Ether price, resulting in short-and long-term forecasts that achieve an accuracy of up to 84.2%.
Bitcoin, one of the major cryptocurrencies, presents great opportunities and\nchallenges with its tremendous potential returns accompanying high risks. The\nhigh volatility of Bitcoin and the complex factors affecting them make the\nstudy of effective price forecasting methods of great practical importance to\nfinancial investors and researchers worldwide. In this paper, we propose a\nnovel approach called MRC-LSTM, which combines a Multi-scale Residual\nConvolutional neural network (MRC) and a Long Short-Term Memory (LSTM) to\nimplement Bitcoin closing price prediction. Specifically, the Multi-scale\nresidual module is based on one-dimensional convolution, which is not only\ncapable of adaptive detecting features of different time scales in multivariate\ntime series, but also enables the fusion of these features. LSTM has the\nability to learn long-term dependencies in series, which is widely used in\nfinancial time series forecasting. By mixing these two methods, the model is\nable to obtain highly expressive features and efficiently learn trends and\ninteractions of multivariate time series. In the study, the impact of external\nfactors such as macroeconomic variables and investor attention on the Bitcoin\nprice is considered in addition to the trading information of the Bitcoin\nmarket. We performed experiments to predict the daily closing price of Bitcoin\n(USD), and the experimental results show that MRC-LSTM significantly\noutperforms a variety of other network structures. Furthermore, we conduct\nadditional experiments on two other cryptocurrencies, Ethereum and Litecoin, to\nfurther confirm the effectiveness of the MRC-LSTM in short-term forecasting for\nmultivariate time series of cryptocurrencies.\n
Abstract Bitcoin has become a commodity traded by millions of traders from all over the world. This is one of the causes of fluctuating price movements. From the data we got on coinmarketcap, Bitcoin is traded on various cryptocurrency trading exchanges. And at every exchange that has a reputation, of course, has an API service to access historical data about the price movements of all the crypto commodities they have traded from the start. By using the PHP programming language and implementation of the CURL function for JSON readings, we can pull Bitcoin movement data in real time. In this paper, Bitcoin is specifically observed because it is the forerunner and the main cryptocurrency commodity traded and is a determinant of Alternative coin price movements in general. In this paper Bitcoin price monitoring is carried out at 30 reputable exchange places through API access provided by each exchange place. Furthermore, conclusions are drawn about the various variants of how to access the API from the 30 bitcoin exchange places. The program code that is displayed directly in this paper can then be used as an initial reference if you want to develop a Cryptocurrency price movement monitoring application for Bitcoin. At the end of the paper, an example of the application of Bitcoin price monitoring will be presented using a web-based application containing charts and supporting indicators as well as a telegram bot to display price depth charts.
The foremost aim of our paper is to predict next-day and any particular month Bitcoin prices with respect to the company as early as possible. To obtain results at the earliest we made our implementation in Apache Spark, a big data tool. We have also utilised one of the widely used machine learning libraries namely pandas for dataset manipulation, and preferred Pyspark since it is the combination of Apache Spark and Python. For investor interaction with our system we have designed a Graphical User Interface (GUI) and named it as ‘PMIST’ with Tkinter which is a Python’s GUI. The result predicted will be seen in the form of line and bar graphs along with a message prompt where right date for doing investments are suggested. By analyzing those graphs, investors can be able to get idea about the future prices and they can take decision to either invest in future or change their investment time. Also a rewarding system is designed for the investors in which we will provide 50% offer in Swiggy when a quiz has been answered correctly. On the whole, this paper is meant for predicting next day and/or any particular month Bitcoin prices along with the rewarding system for the investors.
T. Babatunde Oluwagbenga, Ojo O. Oluwadare, S. Yaya OlaOluwa
This paper tries to identify which class of GARCH variants best describe the volatility of bitcoin prices. The prices of bitcoin from August 7, 2015 to November 28, 2018 with 1210 daily observations were used. Five classical and four fractional integrated GARCH variants were estimated and based on the obtained AIC and SBIC, the four fractional integrated GARCH models fits better than the classical GARCH models. Results further showed that HYGARCH with Generalized error distribution (GED) tends to be the best fitted model for the bitcoin prices with better forecasting performance based on MAPFE and TI measures.
Data collected from social media such as tweets, posts, and blogs can assist in an early indication of market sentiment in the financial field. This has frequently been conducted on Twitter data in particular. Using data mining techniques, opinion mining, machine learning, natural language processing (NLP), and knowledge management, the underlying public mood states and sentiment can be uncovered. As cryptocurrencies play an increasingly significant role in global economies, there is an evident relationship between Twitter sentiment and future price fluctuations in Bitcoin. This paper assesses Tweets' collection, manipulation, and interpretation to predict early market movements of cryptocurrency. More specifically, sentiment analysis and text mining methods, including Logistic Regressions, Binary Classified Vector Prediction, Support Vector Mechanism, and Naive Bayes, were considered. Each model was evaluated on their ability to predict public mood states as measured by `tweets' from Twitter during the era of covid-19. An XGBoost-Composite ensemble model is constructed, which achieved higher performance than the state-of-the-art prediction models.
This paper discusses securities and cryptocurrency trading using artificial intelligence (AI) in the sense that it focuses on performing Exploratory Data Analysis (EDA) on selected technical indicators before proceeding to modelling, and then to develop more practical models by introducing new reward loss function that maximizes the returns during training phase. The results of EDA reveal that the complex patterns within the data can be better captured by discriminative classification models and this was endorsed by performing back-testing on two securities using Artificial Neural Network (ANN) and Random Forests (RF) as discriminative models against their counterpart Naïve Bayes as a generative model. To enhance the learning process, the new reward loss function is utilized to retrain the ANN with testing on AAPL, IBM, BRENT CRUDE and BTC using auto-trading strategy that serves as the intelligent unit, and the results indicate this loss superiorly outperforms the conventional cross-entropy used in predictive models. The overall results of this work suggest that there should be larger focus on EDA and more practical losses in the research of machine learning modelling for stock market prediction applications.
The cryptocurrency market is amongst the fastest-growing of all the financial markets in the world. Unlike traditional markets, such as equities, foreign exchange and commodities, cryptocurrency market is considered to have larger volatility and illiquidity. This paper is inspired by the recent success of using machine learning for stock market prediction. In this work, we analyze and present the characteristics of the cryptocurrency market in a high-frequency setting. In particular, we applied a machine learning approach to predict the direction of the mid-price changes on the upcoming tick. We show that there are universal features amongst cryptocurrencies which lead to models outperforming asset-specific ones. We also show that there is little point in feeding machine learning models with long sequences of data points; predictions do not improve. Furthermore, we solve the technical challenge to design a lean predictor, which performs well on live data downloaded from crypto exchanges. A novel retraining method is defined and adopted towards this end. Finally, the trade-off between model accuracy and frequency of training is analyzed in the context of multi-label prediction. Overall, we demonstrate that promising results are possible for cryptocurrencies on live data, by achieving a consistent 78% accuracy on the prediction of the mid-price movement on live exchange rate of Bitcoins vs. US dollars.
The cryptocurrency price movement behaves randomly and fluctuates like other stock markets. Prediction of cryptocurrency is a recent area of research interest and budding fast. The underlying nonlinearities in its price series make its prediction challenging. Sophisticated methodologies for accurate prediction of cryptocurrency are highly desired. Artificial neural networks (ANNs) are good approximators, however their accuracy is greatly subjective to optimal network structure and learning method. This article designs optimal ANNs for efficient cryptocurrency prediction using quasi opposition based Rao algorithms, i.e. QORA-ANN. The model explores a set of potential ANNs in the search space and lands at an optimal network through the evolving process. Historical data from four emerging cryptocurrencies such as Bitcoin, Litecoin, Ethereum, and Ripple are used to evaluate the QORA-ANN. The prediction ability of the proposed approach is compared with few similar methods such as ANN trained with genetic algorithm, differential evolution and particle swarm optimization (i.e. ANN-GA, ANN-DE, ANN-PSO), support vector machine (SVM), and multilayer perceptron (MLP). From exhaustive simulation studies and comparative result analysis it is found that the QORA-ANN method performed better than others and hence can be suggested as an efficient tool for cryptocurrencies prediction.
This article explores the Bitcoin return predictability of variables constructed from one-minute high-frequency Bitcoin trading data. During the training period of 2012–2018, LASSO is used to pick out the most powerful predictors. We then use predictors selected by LASSO to predict the Bitcoin returns in the 2018–2019 test sample. An investment strategy based on the return predictions outperforms a simple buy-and-hold strategy and other strategies based on the prediction of Ordinary Least Squares and Neural Networks.
The tick rule is one of the most popular trade classification algorithms used when an order initiator in market data is not signed. Using 11.9 million trades of Bitcoin/USD on Bitstamp, this article tests the accuracy of the tick rule in the Bitcoin market. Evidence indicates that the overall success rate of the tick rule is 76.87%. It is also shown that the tick rule is inclined to fail in discerning trade intentions when there is a long period of time between trades. Furthermore, order imbalances computed using the tick rule lack sufficient accuracy in the Bitcoin market.
Blockchain, a shared digital ledger, operates on a peer-to-peer network which is used for storing the transactions. Cryptocurrencies are used for transactions in blockchain. The most popular breed among cryptocurrency was bitcoin. Predicting the day-to-day value of bitcoin is a challenging task due to nonlinear and market volatility. There are many statistical methods and machine learning algorithms proposed to forecast the cost of bitcoin, but they were lacking to predict the correct result when the input data set is larger and has more noise. To handle large data set, a deep learning technique has been used. The deep learning algorithms, especially LSTM network, also have some drawbacks such as high computational time, inability to generate higher quality prediction result. To avoid these shortcomings and make LSTM a better model for bitcoin prediction, it is necessary to optimize LSTM network. This paper presents a comparative study of numerous optimized deep learning techniques to forecast the price of bitcoin.
Abstract From last many years it has been a trend to invest in cryptocurrency especially (Bitcoin) because it is one of the most popular and decentralized digital currency. However, its prices keep on fluctuating very much that makes it difficult to predict. So, our research aim is to find the less time consuming and accurate model for the prediction of Bitcoin price from different machine learning models like (Multivariate Linear Regression, Theil-Sen Regression, Huber Regression) and deep learning algorithms like (LSTM, GRU). The dataset that we will use for our prediction purpose will be stored in MongoDB (Big-Data Tool) because it consists of huge data points. We have also implemented IOT in our system to create an alert system, which alerts user when the value of bitcoin price reaches a threshold value.
Bir paranın sağlam olup olmadığı iki değere bakılarak anlaşılabilmektedir. İlki arzını gösteren stok durumu, ikincisi ise devam eden süreçte üretilecek olan birimi gösteren akış değeridir. Stok ve akış arasındaki oran, para olarak tanımlanan malın sağlamlığının göstergesi olarak ifade edilebilmektedir. Bitcoin, toplam arzı 21.000.000 adet ile sınırlı olan bir kripto paradır. Arzının sınırlı olması, fiyatını yükseltecek bir etmen olarak düşünülmektedir. Stok Akış Modeli de arzı sınırlı olan varlıklar için kullanılabilir. Bu çalışmada zaman serisi analiz modellerinden Facebook Prophet algoritması kullanılarak Bitcoin fiyat tahmini yapılmıştır. 2013-2020 yılları arasındaki günlük verilerin kullanıldığı çalışmada diğer çalışmalardan farklı olarak Stok Akış Modeli’nden elde edilen Stok Akış Oranı da modele eklenmiştir. Doğruluk ölçüleri ile desteklenen çalışma sonuçlarına göre Stok Akış Oranı’nın modele dâhil edilmesi ile Facebook Prophet algoritması kullanıldığında modelin performansının arttığı sonucuna ulaşılmıştır. Son olarak, Prophet yöntemi, ARIMA yöntemine göre daha etkin sonuçlar verdiği elde edilen bulgular arasındadır.
The high volatility of an asset in financial markets is commonly seen as a negative factor. However short-term trades may entail high profits if traders open and close the correct positions. The high volatility of cryptocurrencies, and in particular of Bitcoin, is what made cryptocurrency trading so profitable in these last years. The main goal of this work is to compare several frameworks each other to predict the daily closing Bitcoin price, investigating those that provide the best performance, after a rigorous model selection by the so-called k-fold cross validation method. We evaluated the performance of one stage frameworks, based only on one machine learning technique, such as the Bayesian Neural Network, the Feed Forward and the Long Short Term Memory Neural Networks, and that of two stages frameworks formed by the neural networks just mentioned in cascade to Support Vector Regression. Results highlight higher performance of the two stages frameworks with respect to the correspondent one stage frameworks, but for the Bayesian Neural Network. The one stage framework based on Bayesian Neural Network has the highest performance and the order of magnitude of the mean absolute percentage error computed on the predicted price by this framework is in agreement with those reported in recent literature works.