Bütün sektörler dahilinde finans sektöründe de müşterilere ait fikir ve düşüncelerinin belirlenmesi, firma ve kurumların ileriki dönemler için sunacağı hizmetleri etkilemektedir. Kripto para birimlerinin (Bitcoin, Ethereum, Ripple vb.) ekonomik ve sosyal etkileri hızla artmaya devam ettikçe, ilgili haber makalelerinin ve sosyal medya yayınlarının, özellikle de tweetlerin yaygınlığı da artmaktadır. Bu çalışmada, Twitter kullanıcılarının finans sektörü konularından biri olan Bitcoin ile ilgili yorumları derlenerek bir duygu analizi çalışması yapılmıştır. Kullanıcı yorumları, Twitter’ın sunmuş olduğu API hizmeti vasıtasıyla Python Programlama Dili kullanılarak alınmış; yorumlar olumlu, nötr ve olumsuz etiketler ile ayrıştırılmış, etiket bulutunda toplanmıştır. Naïve Bayes ve Lojistik Regresyon algoritmaları kullanılarak oluşturulan modellerde başarı oranları karşılaştırılmıştır. Naïve Bayes uygulamasının tweetlerin duygularını tahmin etmedeki başarı oranı %72,19 olurken, Lojistik Regresyon uygulamasında bu oran %75,53 olmuştur. Çalışmanın ikinci aşamasında ise, duygu analizinden sonra “Bitcoin” anahtar kelimesi içeren günlük pozitif tweet oranı ile Bitcoin günlük açılış değeri beraber kullanılarak Bitcoin kapanış değeri tahminlemesi yapılmıştır. Finans verileri Yahoo Finance web sitesi üzerinden alınmış; Doğrusal Regresyon ve Rastgele Orman Regresyon yöntemleri ile modeller oluşturulmuştur. Doğrusal Regresyon için r² değeri %88,97 çıkarken, Rastgele Orman Regresyonu için ise %94,16 olmuştur.Anahtar Kelimeler: Duygu analizi, Twitter, Bitcoin, Makine öğrenmesi, Veri madenciliği, Finans
Christoph J. Börner, Ingo Hoffmann, Jonas Krettek, Tim Schmitz
Abstract Cryptocurrencies (CCs) have become increasingly interesting for institutional investors’ strategic asset allocation and will therefore be a fixed component of professional portfolios in the future. However, this asset class differs from established assets primarily in that it has a higher standard deviation and tail risk. The question then arises whether CCs with similar statistical key figures exist. On this basis, a core market incorporating CCs with comparable properties enables the implementation of a tracking error approach. A prerequisite for this is the segmentation of the CC market into a core and a satellite, with the latter comprising the accumulation of the residual CCs remaining in the complement. Using a concrete example, we segment the CC market into these components based on modern methods from image/pattern recognition.
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.
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.
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.
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 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.
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.
The emerging cryptocurrency market has lately received great attention for asset allocation due to its decentralization uniqueness. However, its volatility and brand new trading mode have made it challenging to devising an acceptable automatically-generating strategy. This study proposes a framework for automatic high-frequency bitcoin transactions based on a deep reinforcement learning algorithm-proximal policy optimization (PPO). The framework creatively regards the transaction process as actions, returns as awards and prices as states to align with the idea of reinforcement learning. It compares advanced machine learning-based models for static price predictions including support vector machine (SVM), multi-layer perceptron (MLP), long short-term memory (LSTM), temporal convolutional network (TCN), and Transformer by applying them to the real-time bitcoin price and the experimental results demonstrate that LSTM outperforms. Then an automatically-generating transaction strategy is constructed building on PPO with LSTM as the basis to construct the policy. Extensive empirical studies validate that the proposed method performs superiorly to various common trading strategy benchmarks for a single financial product. The approach is able to trade bitcoins in a simulated environment with synchronous data and obtains a 31.67% more return than that of the best benchmark, improving the benchmark by 12.75%. The proposed framework can earn excess returns through both the period of volatility and surge, which opens the door to research on building a single cryptocurrency trading strategy based on deep learning. Visualizations of trading the process show how the model handles high-frequency transactions to provide inspiration and demonstrate that it can be expanded to other financial products.
We analyze the predictability of the bitcoin market across prediction horizons ranging from 1 to 60 min. In doing so, we test various machine learning models and find that, while all models outperform a random classifier, recurrent neural networks and gradient boosting classifiers are especially well-suited for the examined prediction tasks. We use a comprehensive feature set, including technical, blockchain-based, sentiment-/interest-based, and asset-based features. Our results show that technical features remain most relevant for most methods, followed by selected blockchain-based and sentiment-/interest-based features. Additionally, we find that predictability increases for longer prediction horizons. Although a quantile-based long-short trading strategy generates monthly returns of up to 39% before transaction costs, it leads to negative returns after taking transaction costs into account due to the particularly short holding periods.
Purpose It is crucial to find a better portfolio optimization strategy, considering the cryptocurrencies' asymmetric volatilities. Hence, this research aimed to present dynamic optimization on minimum variance (MVP), equal risk contribution (ERC) and most diversified portfolio (MDP). Design/methodology/approach This study applied dynamic covariances from multivariate GARCH(1,1) with Student’s- t -distribution. This research also constructed static optimization from the conventional MVP, ERC and MDP as comparison. Moreover, the optimization involved transaction cost and out-of-sample analysis from the rolling windows method. The sample consisted of ten significant cryptocurrencies. Findings Dynamic optimization enhanced risk-adjusted return. Moreover, dynamic MDP and ERC could win the naïve strategy (1/N) under various estimation windows, and forecast lengths when the transaction cost ranging from 10 bps to 50 bps. The researcher also used another researcher's sample as a robustness test. Findings showed that dynamic optimization (MDP and ERC) outperformed the benchmark. Practical implications Sophisticated investors may use the dynamic ERC and MDP to optimize cryptocurrencies portfolio. Originality/value To the best of the author’s knowledge, this is the first paper that studies the dynamic optimization on MVP, ERC and MDP using DCC and ADCC-GARCH with multivariate- t- distribution and rolling windows method.
Paolo De Angelis, Roberto De Marchis, Mario Marino, Antonio Luciano Martire · 5 authors
Abstract In this paper, we come up with an original trading strategy on Bitcoins. The methodology we propose is profit-oriented , and it is based on buying or selling the so-called Contracts for Difference, so that the investor’s gain, assessed at a given future time t , is obtained as the difference between the predicted Bitcoin price and an apt threshold. Starting from some empirical findings, and passing through the specification of a suitable theoretical model for the Bitcoin price process, we are able to provide possible investment scenarios, thanks to the use of a Recurrent Neural Network with a Long Short-Term Memory for predicting purposes.
Στόχος της παρούσας μελέτης ήταν η διερεύνηση της συμπεριφοράς των τιμών πέντε κρυπτονομισμάτων BTC, LTC, ETH, XMR και XRP, των διακυμάνσεων, των πιθανών μέγιστων τιμών, των ελάχιστων τιμών και εάν υπάρχει σύνδεση, συνεργασία στη συμπεριφορά των κρυπτονομισμάτων. Για τον λόγο αυτό, οι ημερήσιες τιμές των πέντε κρυπτονομισμάτων από το 2013 έως το 2020 ανακτήθηκαν από την ιστοσελίδα www.coinmarketcap.com. Αρχικά, πραγματοποιήθηκε ανάλυση συσχέτισης με τη χρήση κυλιόμενου παραθύρου 100 ημερών κάθε ζεύγους κρυπτονομισμάτων, BTC - LTC, BTC - ETH, BTC - XMR, BTC - XRP, LTC - ETH, LTC - XMR, LTC - XRP, ETH - XMR, ETH - XRP και XMR – XRP. Επίσης, πραγματοποιήθηκε μια ανάλυση συνολοκλήρωσης με τη χρήση της δοκιμής Johansen. Η ανάλυση κυλιόμενης συσχέτισης κατέληξε στο συμπέρασμα ότι και τα πέντε κρυπτονομίσματα πριν από το έτος 2017 παρουσίασαν ένα ασταθές μοτίβο. Εν αντιθέσει, μετά το 2017, το επίπεδο συσχέτισης ήταν υψηλότερο από 0,6 και για τα πέντε κρυπτονομίσματα το οποίο αποτελεί ένδειξη σταθερού και παρόμοιου μοτίβου μεταξύ των κρυπτονομισμάτων. Τέλος, η ανάλυση δοκιμής Johansen/συνολοκλήρωσης κατέληξε στο συμπέρασμα ότι υπήρξε μια εξίσωση συνολοκλήρωσης για την περίοδο 2017 έως το 2020. Αυτό το αποτέλεσμα ήταν σύμφωνο με το αποτέλεσμα της ανάλυσης κυλιόμενου παραθύρου.
Marco Ortu, Nicola Uras, Claudio Conversano, Giuseppe Destefanis · 5 authors
This work aims to analyse the predictability of price movements of\ncryptocurrencies on both hourly and daily data observed from January 2017 to\nJanuary 2021, using deep learning algorithms. For our experiments, we used\nthree sets of features: technical, trading and social media indicators,\nconsidering a restricted model of only technical indicators and an unrestricted\nmodel with technical, trading and social media indicators. We verified whether\nthe consideration of trading and social media indicators, along with the\nclassic technical variables (such as price's returns), leads to a significative\nimprovement in the prediction of cryptocurrencies price's changes. We conducted\nthe study on the two highest cryptocurrencies in volume and value (at the time\nof the study): Bitcoin and Ethereum. We implemented four different machine\nlearning algorithms typically used in time-series classification problems:\nMulti Layers Perceptron (MLP), Convolutional Neural Network (CNN), Long Short\nTerm Memory (LSTM) neural network and Attention Long Short Term Memory (ALSTM).\nWe devised the experiments using the advanced bootstrap technique to consider\nthe variance problem on test samples, which allowed us to evaluate a more\nreliable estimate of the model's performance. Furthermore, the Grid Search\ntechnique was used to find the best hyperparameters values for each implemented\nalgorithm. The study shows that, based on the hourly frequency results, the\nunrestricted model outperforms the restricted one. The addition of the trading\nindicators to the classic technical indicators improves the accuracy of Bitcoin\nand Ethereum price's changes prediction, with an increase of accuracy from a\nrange of 51-55% for the restricted model, to 67-84% for the unrestricted model.\n
The present study aims to establish the model of the cryptocurrency price trend based on financial theory using the LSTM model with multiple combinations between the window length and the predicting horizons, the random walk model is also applied with different parameter settings.