Sentiments are extracted from tweets with the hashtag of cryptocurrencies to predict the price and sentiment prediction model generates the parameters for optimization procedure to make decision and re-allocate the portfolio in the further step. Moreover, after the process of prediction, the evaluation, which is conducted with RMSE, MAE and R2, select the KNN and CART model for the prediction of Bitcoin and Ethereum respectively. During the process of portfolio optimization, this project is trying to use predictive prescription to robust the uncertainty and meanwhile take full advantages of auxiliary data such as sentiments. For the outcome of optimization, the portfolio allocation and returns fluctuate acutely as the illustration of figure.
Many traders believe in and use Twitter tweets to guide their daily cryptocurrency trading. In this project, we investigated the feasibility of automated sentiment analysis for cryptocurrencies. For the study, we targeted one cryptocurrency (NEO) altcoin and collected related data. The data collection and cleaning were essential components of the study. First, the last five years of daily tweets with NEO hashtags were obtained from Twitter. The collected tweets were then filtered to contain or mention only NEO. We manually tagged a subset of the tweets with positive, negative, and neutral sentiment labels. We trained and tested a Random Forest classifier on the labeled data where the test set accuracy reached 77%. In the second phase of the study, we investigated whether the daily sentiment of the tweets was correlated with the NEO price. We found positive correlations between the number of tweets and the daily prices, and between the prices of different crypto coins. We share the data publicly.
Jongyeop Kim, Hayden Wimmer, Hong Liu, Seong-Soo Kim
Big data analysis for accurate predictions requires adherence to systematic procedures. This study shows an entire data analysis phase from the data collection to model evaluation using the Long Short-Term memory(LSTM) for cryptocurrency price prediction. Three different coin prices are directly collected from the CoinMarketCap in nearly real-time by applying the web scraping technique. The LSTM model trained with this data varying random seed or static seed parameters to find optimal conditions, leading to better accuracy of the LSTM model. Our model evaluated their accuracy in terms of MAE, RMSE, and SMAPE indicators. As a result of this experiment, most of the best candidate parameters are classified at the fixed seed trail in terms of the RMSE for Bit coin, Ethereum, and Lite Coin.
Jongyeop Kim, Seong-Soo Kim, Hayden Wimmer, Hong Liu
This study aims to predict cryptocurrency prices using Long Short-Term Memory(LSTM) and Gated Recurrent Unit(GRU) for three different coins: BitCoin, Ethereum, and Litecoin. For the training data for prediction, two data sets with different statistical characteristics in terms of Kurtosis and Skewness are used. LSTM and GRU models are trained and tested on the same hyperparameter configuration while increasing the number of epochs from 1 to 30. The accuracy of each model is measured by Root Mean Square Error (RMSE) and MAE (Mean Absolute Error). As a result of comparing GRU and LSTM, in BTC and ETH, the GRU was more advantageous for the downward stabilization trend, and the LSTM was suitable for the upward stabilization trend. However, in case of low-priced LTC, LSTM and GRU showed the same performance in sample type A, and in the case of type B, GRU was more accurate.
Cryptocurrency or virtual currency is a form of investment that has developed since 2010. Today, there are more than 2,000 types of crypto currencies worldwide. Cryptocurrency research in Indonesia is still focused on the legal status and legal status of cryptocurrency investments. This quantitative descriptive study aims to describe the returns and risks of investing in crypto currencies. Descriptive analysis by calculating risk measures and using the heteroscedastic model GARCH (1,1) was carried out on the return data of 15 crypto currencies that had the greatest value. Information was obtained that investing in most crypto currencies resulted in higher returns than investing in foreign currencies or the stock market. On the other hand, Crypto currencies have a higher risk of loss and volatility clustering or heteroscedasticity. Further research is needed to uncover the characteristics of Crypto currency returns and their performance in the form of a portfolio.
This paper initially presents a nontechnical overview of cryptocurrency, its history, and the technicalities of its usage as a means of exchange. Bitcoin’s working methodology and mathematical baseline is further presented in more depth. For the remaining majority of the paper, recent cryptocurrency price data of Bitcoin, Ethereum, Tether, Dogecoin, and Binance coin was used to train a machine learning model of Feed Forward Neural Networks to predict future prices for each of the datasets. Further and in conclusion, the results are discussed, and the efficiency and accuracy of these models are evaluated.
Fahad Mostafa, Pritam Saha, Mohammad Rafiqul Islam, Nguyet Nguyen
Cryptocurrencies are currently traded worldwide, with hundreds of different currencies in existence and even more on the way. This study implements some statistical and machine learning approaches for cryptocurrency investments. First, we implement GJR-GARCH over the GARCH model to estimate the volatility of ten popular cryptocurrencies based on market capitalization: Bitcoin, Bitcoin Cash, Bitcoin SV, Chainlink, EOS, Ethereum, Litecoin, TETHER, Tezos, and XRP. Then, we use Monte Carlo simulations to generate the conditional variance of the cryptocurrencies using the GJR-GARCH model, and calculate the value at risk (VaR) of the simulations. We also estimate the tail-risk using VaR backtesting. Finally, we use an artificial neural network (ANN) for predicting the prices of the ten cryptocurrencies. The graphical analysis and mean square errors (MSEs) from the ANN models confirmed that the predicted prices are close to the market prices. For some cryptocurrencies, the ANN models perform better than traditional ARIMA models.
Bitcoin has attracted attention from different market participants due to unpredictable price patterns. Sometimes, the price has exhibited big jumps. Bitcoin prices have also had extreme, unexpected crashes. We test the predictive power of a wide range of determinants on bitcoins’ price direction under the continuous transfer entropy approach as a feature selection criterion. Accordingly, the statistically significant assets in the sense of permutation test on the nearest neighbour estimation of local transfer entropy are used as features or explanatory variables in a deep learning classification model to predict the price direction of bitcoin. The proposed variable selection do not find significative the explanatory power of NASDAQ and Tesla. Under different scenarios and metrics, the best results are obtained using the significant drivers during the pandemic as validation. In the test, the accuracy increased in the post-pandemic scenario of July 2020 to January 2021 without drivers. In other words, our results indicate that in times of high volatility, Bitcoin seems to self-regulate and does not need additional drivers to improve the accuracy of the price direction.
Bitcoin is one of the cryptocurrencies that had a high rate of return since its appearance in 2009. However, the exchange rate of Bitcoin against any foreign currency is considered to have high volatility making it difficult to determine the real value of Bitcoin. The main purpose of this research is to find the value of Bitcoin, especially US Dollar and Rupiah currencies. The test is carried out using the weak market efficiency hypothesis and the semi-form market coefficient hypothesis. The data processing methods are used the stationary test (ADF, KPSS, and ERS) to test the efficiency of the weak form market and the cointegration test (Johansen Cointegration) with the VECM model to check the efficiency of the semi-strong market. The results show that the Bitcoin exchange rate does not have a unit root so it is inefficient in a weak form and has a negative effect on the USD / IDR exchange rate so that it is not efficient in semi-strong form as well as on the US Dollar and Rupiah exchange rates. This happens because Bitcoin transactions as a medium of exchange in Indonesia are still illegal. So that the Bitcoin exchange rate against the US Dollar and Rupiah exchange rates is biased because it does not reflect the available information, both historical information and public information. Keywords—Bitcoin Exchange Rate; Market Efficiency; Unit Root; Cointegration
Natalia A. Van Heerden, Juan Cabral, Nadia Luczywo
In recent years, cryptocurrencies have gone from an obscure niche to a prominent place, with investment in these assets becoming increasingly popular. However, cryptocurrencies carry a high risk due to their high volatility. In this paper, criteria based on historical cryptocurrency data are defined in order to characterize returns and risks in different ways, in short time windows (7 and 15 days); then, the importance of criteria is analyzed by various methods and their impact is evaluated. Finally, the future plan is projected to use the knowledge obtained for the selection of investment portfolios by applying multi-criteria methods.
This paper proposes prediction of the bitcoin return direction with logistic, discriminant analysis and machine learning classification techniques. It extends the prediction of the bitcoin return direction using exogenous macroeconomic and financial variables which have been investigated as drivers of bitcoin return. We also use google trends as proxy for investors interest on bitcoin. We consider those variables as predictors for bitcoin return direction. We conduct an in-sample and out-of-sample empirical analysis and achieve a misclassification error around 4% for in-sample evaluation and around 41% in out-of-sample empirical analysis. Ensemble learning trees based outperforms the other methods in both in-sample and out-of-sample analyses.
The world first decentralized currency - cryptocurrency brings us the new era of a mode of exchange. It has been included many technologies like bitcoin, ethereum, and hyper ledger. Due to its rising popularity and demand, people are often curious to know the future price of these coins to make a good deal with them. The future price of bitcoin would help investors as well as corporate to get an overview of the demand and role in the economy. Many researchers have investigated various solutions that will predict the future price of bitcoin. But, the solutions achieved low accuracy. This paper main aim is to propose a prediction model that will predict the future price of bitcoin. The model is based on the deep learning approaches. The proposed model included four different deep learning models. These models are Long Short-Term Memory (LSTM), Bidirectional LSTM, Gated Recurrent Unit (GRU), and Bidirectional GRU. The performance of the prediction models is computed and it found Bi-GRU gave the best-predicted results.
Digital currency aims to decentralize online transactions with high efficiency and increased security. These operations are carried out using blockchain based systems to eliminate the need for centralized verification and authorization. With the emergence of these systems come a vast number of cryptocurrencies such as bitcoins and ether that are widely used. The need for the analysis of the trend of digital currency arises because of the frequent fluctuation of their value in the markets. In this paper, the prediction of the trend of one such cryptocurrency, bitcoins, is performed using a Deep Belief Network model that is pre-trained using Restricted Boltzmann Machines for studying the data for 2019 with different time intervals: minute-by-minute, hour-by-hour and day-by-day. This would help to identify the trend of the cryptocurrency bitcoin for analyzing the demand supply dynamics of their market capital. The trained model was evaluated with the measures of MAE, MSE and compared with the existing state-of-the-art models. The minute-by-minute prediction model performed best with a RMSE of 25.87 and a MAE of 14.83.
Cryptocurrencies such as bitcoin have garnered a lot of attention in recent months due to their meteoric rise. In this paper, we propose a new method for predicting the direction of bitcoin price using linear discriminant analysis (LDA) together with sentiment analysis. Concretely, we train an LDA-based classifier that uses the current bitcoin price information and Twitter headline news in order to forecast the next-day direction of bitcoin price. The proposed model achieves highly accurate results beating several benchmark targets. In particular, the proposed approach produces forecast accuracy of 0.828 and AUC of 0.840 on the test data.
Yuze Li, Shangrong Jiang, Yunjie Wei, Shouyang Wang
Abstract The emergence and growing popularity of Bitcoins have attracted the attention of the financial world. However, few empirical studies have considered the inclusion of the newly emerged commodity asset in the global commodity market. It is of great importance for investors and policymakers to take advantage of this asset and its potential benefits by incorporating it as a part of the broad commodity trading portfolio. In this study, we propose a novel ensemble portfolio optimization (NEPO) framework utilized for broad commodity assets, which integrates a hybrid variational mode decomposition-bidirectional long short-term memory deep learning model for future returns forecast and a reinforcement learning-based model for optimizing the asset weight allocation. Our empirical results indicate that the NEPO framework could effectively improve the prediction accuracy and trend prediction ability across various commodity assets from different sectors. In addition, it could effectively incorporate Bitcoins into the asset pool and achieve better financial performance compared to traditional asset allocation strategies, commodity funds, and indices.
Cryptocurrency is an advanced digital currency that is gotten by cryptography, numerous digital currencies are decentralized organizations dependent on blockchain innovation an appropriated record authorized by a different organization of computers. And Many present-day technologies are driving the transformative impact in the global financial system, in that impact cryptocurrency stands on first position in the list. Cryptocurrency offer several potential benefits, including better speed and efficiency in processing payments and transfers notably across borders and ultimately boosting financial inclusion. The intension of this paper is to summaries the difference between the normal or traditional method of currency transaction and crypto currency transaction. And why all are providing more interest towards crypto methods nowadays and what different they feel while choosing a crypto method over a normal or traditional currency methods. And how crypto currency is dragging current world attention towards its pocket and why many are developing interest towards following the crypto trend.
This work presents an application of self-attention networks for cryptocurrency trading. Cryptocurrencies are extremely volatile and unpredictable. Thus, cryptocurrency trading is challenging and involves higher risks than trading traditional financial assets such as stocks. To overcome the aforementioned problems, we propose a deep reinforcement learning (DRL) approach for cryptocurrency trading. The proposed trading system contains a self-attention network trained using an actor-critic DRL algorithm. Cryptocurrency markets contain hundreds of assets, allowing greater investment diversification, which can be accomplished if all the assets are analyzed against one another. Self-attention networks are suitable for dealing with the problem because the attention mechanism can process long sequences of data and focus on the most relevant parts of the inputs. Transaction fees are also considered in formulating the studied problem. Systems that perform trades in high frequencies cannot overlook this issue, since, after many trades, small fees can add up to significant expenses. To validate the proposed approach, a DRL environment is built using data from an important cryptocurrency market. We test our method against a state-of-the-art baseline in two different experiments. The experimental results show the proposed approach can obtain higher daily profits and has several advantages over existing methods.
Chidi U. Okonkwo, Bright O. Osu, Farid Chighoub, Ben I. Oruh
This paper investigated the co-movement between the bitcoin (BTC) and the exchange rates of some African currencies to the USD (United States Dollars) using the continuous wavelet transform (CWT) and wavelet coherence (WTC). This was done for the noisy as well as the denoised series. The CWT for the noisy series suggests high volatility for those who hold the currencies for the short term and low volatility for those who hold the currencies for a long-term period. The CWT of the denoised series suggests that volatility at low frequency is driven by noise, while volatility at a higher frequency is driven by market forces. The wavelet coherence suggests that in the presence of noise, bitcoin will be a hedge for the currencies. However, in the absence of noise, bitcoin is a haven for the Egyptian EGP, followed by the Algerian DZD, then the Nigerian NGN, and may not be a haven for the South African ZAR.