Bitcoin (BTC)-the first cryptocurrency-is a decentralized network used to make private, anonymous, peer-to-peer transactions worldwide, yet there are numerous issues in its pricing due to its arbitrary nature, thus limiting its use due to skepticism among businesses and households. However, there is a vast scope of machine learning approaches to predict future prices precisely. One of the major problems with previous research on BTC price predictions is that they are primarily empirical research lacking sufficient analytical support to back up the claims. Therefore, this study aims to solve the BTC price prediction problem in the context of both macroeconomic and microeconomic theories by applying new machine learning methods. Previous work, however, shows mixed evidence of the superiority of machine learning over statistical analysis and vice versa, so more research is needed. This paper applies comparative approaches, including ordinary least squares (OLS), Ensemble learning, support vector regression (SVR), and multilayer perceptron (MLP), to investigate whether the macroeconomic, microeconomic, technical, and blockchain indicators based on economic theories predict the BTC price or not. The findings point out that some technical indicators are significant short-run BTC price predictors, thus confirming the validity of technical analysis. Moreover, macroeconomic and blockchain indicators are found to be significant long-term predictors, implying that supply, demand, and cost-based pricing theories are the underlying theories of BTC price prediction. Likewise, SVR is found to be superior to other machine learning and traditional models. This research's innovation is looking at BTC price prediction through theoretical aspects. The overall findings show that SVR is superior to other machine learning models and traditional models. This paper has several contributions. It can contribute to international finance to be used as a reference for setting asset pricing and improved investment decision-making. It also contributes to the economics of BTC price prediction by introducing its theoretical background. Moreover, as the authors still doubt whether machine learning can beat the traditional methods in BTC price prediction, this research contributes to machine learning configuration and helping developers use it as a benchmark.
Abstract This paper explores the use of machine learning algorithms and narrative sentiments when applied to the task of forecasting and trading Bitcoin. The forecasting framework starts from the selection among 295 individual prediction models. Three machine learning approaches, namely, neural networks, support vector machines, and gradient boosting approach, are used to further improve the forecasting performance of individual models. By taking data‐snooping bias into account, three different metrics are applied to examine the forecasting ability of each model. Our results suggest that the machine learning techniques always outperform the best individual model whereas the gradient boosting framework has the best performance among all the models. Finally, a time‐varying leverage trading strategy combined with narrative sentiments and volatility is proposed to enhance trading performance. This suggests that the hybrid leverage strategy provides the highest Bitcoin profits consistently among all trading exercises.
Abstract Cryptocurrencies are distributed digital currencies that have emerged as a consequence of financial technology advancement. In 2017, cryptocurrencies have shown a huge rise in their market capitalization and popularity. They are now employed in today’s financial systems as individual investors, corporate firms, and big institutions are heavily investing in them. However, this industry is less stable than traditional currency markets. It can be affected by several legal, sentimental, and technical factors, so it is highly volatile, dynamic, uncertain, and unpredictable, hence, accurate forecasting is essential. Recently, cryptocurrency price prediction becomes a trending research topic globally. Various machine and deep learning algorithms, e.g., Neural Networks (NN), Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM) were utilized to analyze the factors influencing the prices of the cryptocurrencies and accordingly predict them. This paper suggests a five-phase framework for cryptocurrency price prediction based on two state-of-the-art deep learning architectures (i.e., BiLSTM and GRU). The current study uses three public real-time cryptocurrency datasets from “Yahoo Finance”. Bidirectional Long Short-Term Memory and Gated Recurrent Unit deep learning-based algorithms are used to forecast the prices of three popular cryptocurrencies (i.e., Bitcoin, Ethereum, and Cardano). The Grid Search approach is used for the hyperparameters optimization processes. Results indicate that GRU outperformed the BiLSTM algorithm for Bitcoin, Ethereum, and Cardano, respectively. The lowest RMSE for the GRU model was found to be 0.01711, 0.02662, and 0.00852 for Bitcoin, Ethereum, and Cardano, respectively. Experimental results proved the significant performance of the proposed framework that achieves the minimum MSE and RMSE values.
Cryptocurrency markets have attracted many interest for global investors because of their novelty, wide on-line availability, increasing capitalization, and potential profits. In the econophysics tradition, we show that many of the most available cryptocurrencies have return statistics that do not follow Gaussian distributions, instead following heavy-tailed distributions. Entropy measures are applied, showing that portfolio diversification is a reasonable practice for decreasing return uncertainty.
The cryptocurrency market has received much interest in the media and academia because of its large price fluctuations since the beginning of 2013. By looking into the impact of behavioral finance elements on investing decisions in the cryptocurrency market, investors who invest in the cryptocurrency market will be able to make better decisions. Based on studies on its principal currency, the 18th of December 2017 has been designated as the peak date of the cryptocurrency market's greatest bubble. A bibliometric approach by means of quantitative analytical methods was applied to discover the relationship between the keywords associated with cryptocurrency and behavioral finance. Articles were extracted from the Scopus database that was published between 2018 and 2021. Publication Year, nation, area of research, journal, authors, and organizational affiliations were all examined in the extracted records. The VOSviewer application was used to visualise relation between both the research themes. Analysis of 102 review and original articles exposed that the total number of publications has incessantly increased over the last 4 years. This study examines the countries that contribute more publications in the selected field of research. The current study uses bibliometric approaches to evaluate cryptocurrency research and highlighted current trends in the interaction between cryptocurrencies and behavioural finance using several metrics, as well as prospective future research hot spots in this sector.
Analyzing comovements and connectedness is critical for providing significant implications for crypto-portfolio risk management. However, most existing research focuses on the lower-order moment nexus (i.e. the return and volatility interactions). For the first time, this study investigates the higher-order moment comovements and risk connectedness among cryptocurrencies before and during the COVID-19 pandemic in both the time and frequency domains. We combine the realized moment measures and wavelet coherence, and the newly proposed time-varying parameter vector autoregression-based frequency connectedness approach (Chatziantoniou et al. in Integration and risk transmission in the market for crude oil a time-varying parameter frequency connectedness approach. Technical report, University of Pretoria, Department of Economics, 2021) using intraday high-frequency data. The empirical results demonstrate that the comovement of realized volatility between BTC and other cryptocurrencies is stronger than that of the realized skewness, realized kurtosis, and signed jump variation. The comovements among cryptocurrencies are both time-dependent and frequency-dependent. Besides the volatility spillovers, the risk spillovers of high-order moments and jumps are also significant, although their magnitudes vary with moments, making them moment-dependent as well and are lower than volatility connectedness. Frequency connectedness demonstrates that the risk connectedness is mainly transmitted in the short term (1-7 days). Furthermore, the total dynamic connectedness of all realized moments is time-varying and has been significantly affected by the outbreak of the COVID-19 pandemic. Several practical implications are drawn for crypto investors, portfolio managers, regulators, and policymakers in optimizing their investment and risk management tactics.
Christoph Schlegel, Mateusz Kwaśnicki, Akaki Mamageishvili
We study axiomatic foundations for different classes of constant-function automated market makers (CFMMs). We focus particularly on separability and on different invariance properties under scaling. Our main results are an axiomatic characterization of a natural generalization of constant product market makers (CPMMs), popular in decentralized finance, on the one hand, and a characterization of the Logarithmic Scoring Rule Market Makers (LMSR), popular in prediction markets, on the other hand. The first class is characterized by the combination of independence and scale invariance, whereas the second is characterized by the combination of independence and translation invariance. The two classes are therefore distinguished by a different invariance property that is motivated by different interpretations of the numéraire in the two applications. However, both are pinned down by the same separability property. Moreover, we characterize the CPMM as an extremal point within the class of scale invariant, independent, symmetric AMMs with non-concentrated liquidity provision. Our results add to a formal analysis of mechanisms that are currently used for decentralized exchanges and connect the most popular class of DeFi AMMs to the most popular class of prediction market AMMs.
Virtual digital assets including cryptocurrencies, non-fungible tokens and decentralized financial asset have been initially used as an alternative currency but are currently being purchased as an asset and hedging instruments. Exponentially growing trading volume witnesses the growing inclination of investors towards these assets, and this calls for volatility analysis of these assets. In this reference, the present study assessed and compared the volatility of returns from investment in virtual digital assets, equity and commodity market. Daily closing prices of selected cryptocurrencies, non-fungible tokens and decentralized financial assets, stock indices and commodities have been analysed for the post-covid period. Since returns were observed to be heteroscedastic, autoregressive conditional heteroscedastic models have been used to assess the volatility. The results indicate a low correlation of commodity investment with all other investment opportunities. Also, Tether and Dai have been observed to be negatively correlated with stock market. This indicates the possibility of minimizing risk through portfolio diversification. In terms of average returns, virtual digital assets are discerned to be better options than equity stock or commodity yet the variance scenario of these investment avenues is not very rosy. The volatility parameters reveal that unlike commodity market, virtual digital assets have got a significant impact of external shocks in the short-run. Further, the long run persistency of shocks is observed to be higher for the UK stock market, followed by Ethereum, Tether and Dai. The present analysis is crucial as the decision about its acceptance as legal tender money is still sub-judice in some countries. The results are expected to provide insight to regulatory bodies about these assets.
The study proposes a quote-driven predictive automated market maker (AMM) platform with on-chain custody and settlement functions, alongside off-chain predictive reinforcement learning capabilities to improve liquidity provision of real-world AMMs. The proposed AMM architecture is an augmentation to the Uniswap V3, a cryptocurrency AMM protocol, by utilizing a novel market equilibrium pricing for reduced divergence and slippage loss. Further, the proposed architecture involves a predictive AMM capability, utilizing a deep hybrid Long Short-Term Memory (LSTM) and Q-learning reinforcement learning framework that looks to improve market efficiency through better forecasts of liquidity concentration ranges, so liquidity starts moving to expected concentration ranges, prior to asset price movement, so that liquidity utilization is improved. The augmented protocol framework is expected have practical real-world implications, by (i) reducing divergence loss for liquidity providers, (ii) reducing slippage for crypto-asset traders, while (iii) improving capital efficiency for liquidity provision for the AMM protocol. To our best knowledge, there are no known protocol or literature that are proposing similar deep learning-augmented AMM that achieves similar capital efficiency and loss minimization objectives for practical real-world applications.
The present study examines the nonlinear relationship between the bitcoin prices and total bitcoin energy consumption over the period November 2010 and October 2021. A discrete threshold regression (TR) model is deployed to estimate the unknown thresholds that trigger the Bitcoin prices regime change. The designated TR model identifies six regimes of change for Bitcoin price movements. The estimated critical threshold specifications (total bitcoin energy consumption) that trigger the regime change of Bitcoin prices are estimated as 0.13, 2.52, 14.06, 43.17, and 146.29 respectively. The study finds that the impact of total bitcoin energy consumption on bitcoin prices are only statistically significant in the higher (4th and 6th) regimes respectively. The message here is that the impact of total bitcoin energy consumption on bitcoin prices is not uniform.
A year ago, one thousand USD invested in Bitcoin (BTC) alone would have appreciated to three thousand five hundred USD. Deep reinforcement learning (DRL) recent outstanding performance has opened up the possibilities to predict price fluctuations in changing markets and determine effective trading points, making a significant contribution to the finance sector. Several DRL methods have been tested in the trading domain. However, this research proposes implementing the proximal policy optimisation (PPO) algorithm, which has not been integrated into an automated trading system (ATS). Furthermore, behavioural biases in human decision-making often cloud one’s judgement to perform emotionally. ATS may alleviate these problems by identifying and using the best potential strategy for maximising profit over time. Motivated by the factors mentioned, this research aims to develop a stable, accurate, and robust automated trading system that implements a deep neural network and reinforcement learning to predict price movements to maximise investment returns by performing optimal trading points. Experiments and evaluations illustrated that this research model has outperformed the baseline buy and hold method and exceeded models of other similar works.
This paper aims to study the investment strategy of gold and bitcoin markets and look for a better solution in the investment market to obtain more profits. We first analyze and forecast the gold and bitcoin markets by establishing several models, and find out the model that can best fit gold and bitcoin. Then, based on the optimal models, the most appropriate investment algorithm is proposed to help investors make decisions on every day's investment in order to reap the greatest rewards.
How to predict the change trend of asset prices in the future and decide different operation modes in advance to obtain the maximum benefits is the concern of investors. Taking gold and bitcoin as examples, this paper develops an appropriate mathematical model that uses only the past daily price stream to help traders determine whether to buy, hold or sell assets in their portfolio every day. At the same time, the robustness of the model is analyzed by robustness. The study found that holding US $1000 on September 11, 2016 will eventually maximize profits on September 10, 2021.
As cryptocurrencies become the target of many investors, it is speculated that there may be a correlation between the trading prices of cryptocurrencies and other assets (e.g., TESLA and BITCOIN). On this basis, we try to build an arbitrage model among the TESLA, BITCOIN, and DOGECOIN to validate the feasibility by simulations using their trading data for 5 years. After conducting the Augmented Dickey-Fuller test, Co-integration test, etc., TESLA and BITCOIN are best correlated that co-integrated over a relatively long period. Within the range of co-integration, we construct the arbitrage model and design the transaction signals by setting a certain threshold. Subsequently, backtestings are carried out accordingly, where different spreads as trading thresholds lead to different results with large differences in returns. These results shed light on the decision on arbitrage investments for cryptocurrencies and other assets.
Maximizing returns has always been people's investment goal. Gold and bitcoin are popular with investors because of their hedges and volatility. However, markets are risky and can be influenced by different economic, political and environmental factors. As a result, bitcoin and gold prices fluctuate wildly, leading to uncertain investment and uncertain returns. In order to maximize the profit, this paper completes the data processing and model construction to make decisions. Based on the Markov decision process of avoiding risk avoidance, reducing transaction cost and maintaining liquidity, and assuming that the stock market is not affected by enhanced trading agent, deep reinforcement learning (DRL) is used to simulate stock trading. The application of the model is helpful to forecast the return of investment portfolio and brings strong application value to the relevant practitioners.
For a long time predicting, studying and analyzing financial indices has been of major interest for the financial community. Recently, there has been a growing interest in the Deep-Learning community to make use of reinforcement learning which has surpassed many of the previous benchmarks in a lot of fields. Our method provides a feature rich environment for the reinforcement learning agent to work on. The aim is to provide long term profits to the user so, we took into consideration the most reliable technical indicators. We have also developed a custom indicator which would provide better insights of the Bitcoin market to the user. The Bitcoin market follows the emotions and sentiments of the traders, so another element of our trading environment is the overall daily Sentiment Score of the market on Twitter. The agent is tested for a period of 685 days which also included the volatile period of Covid-19. It has been capable of providing reliable recommendations which give an average profit of about 69%. Finally, the agent is also capable of suggesting the optimal actions to the user through a website. Users on the website can also access the visualizations of the indicators to help fortify their decisions.
Designing profitable and reliable trading strategies is challenging in the highly volatile cryptocurrency market. Existing works applied deep reinforcement learning methods and optimistically reported increased profits in backtesting, which may suffer from the false positive issue due to overfitting. In this paper, we propose a practical approach to address backtest overfitting for cryptocurrency trading using deep reinforcement learning. First, we formulate the detection of backtest overfitting as a hypothesis test. Then, we train the DRL agents, estimate the probability of overfitting, and reject the overfitted agents, increasing the chance of good trading performance. Finally, on 10 cryptocurrencies over a testing period from 05/01/2022 to 06/27/2022 (during which the crypto market crashed two times), we show that the less overfitted deep reinforcement learning agents have a higher return than that of more overfitted agents, an equal weight strategy, and the S&P DBM Index (market benchmark), offering confidence in possible deployment to a real market.
Moudher Kh. Abdal-Hammed, Afraa Ghazal, Hendra Ibrahim, Akhil Ahmed
redicting currency rates is important, for everyone who is trading and trying to build an investment portfolio from a range of crypto currencies. It is not subject to the same restrictions as fiat currencies. In this study, we seek to predict the exchange rate of BIT-COIN against the US dollar. The short-term data (365 observations) is processed using the LSTM model as one of the neural network models. Modeling is conducted by training a sample size of 67%, taking into account sharp fluctuations in the price of trade and a certain level of market efficiency. The GARCH model is used to select appropriate historical periods for how the LSTM model works and to test proficiency at the weak, semi-strong, and strong levels. The data series obtained from the website (Investing.com) have been processed. The researchers have found that the performance of the neural network improves as the EPOCH value increases with a training (research) period of 50 days before, which is consistent with the results of the proficiency test at the weak level. It agrees with the results of the sufficiency test at the weak level, which indicates that in the case under study (the Bitcoin market is effective at the weak level). It is advised that crypto-currency investors rely more on the historical trend of the price of the currency than on its current price, taking advantage of the artificial neural network model (LSTM) in dealing with little data of high volatility.
Experimental data was obtained from Bitcoin public library made available at https://www.investing.com/crypto/bitcoin/historical-dat which has attributes: open price, high, low and closes as shown in Table 1.
Sang-Ha Sung, Jong‐Min Kim, Byung-Kwon Park, Sangjin Kim
Cryptocurrencies are highly volatile investment assets and are difficult to predict. In this study, various cryptocurrency data are used as features to predict the log-return price of major cryptocurrencies. The original contribution of this study is the selection of the most influential major features for each cryptocurrency using the volatility features of cryptocurrency, derived from the autoregressive conditional heteroskedasticity (ARCH) and generalized autoregressive conditional heteroskedasticity (GARCH) models, along with the closing price of the cryptocurrency. In addition, we sought to predict the log-return price of cryptocurrencies by implementing various types of time-series model. Based on the selected major features, the log-return price of cryptocurrency was predicted through the autoregressive integrated moving average (ARIMA) time-series prediction model and the artificial neural network-based time-series prediction model. As a result of log-return price prediction, the neural-network-based time-series prediction models showed superior predictive power compared to the traditional time-series prediction model.
Abstract Nowadays, the issue of fluctuations in the price of digital Bitcoin currency has a striking impact on the profit or loss of people, international relations, and trade. Accordingly, designing a model that can take into account the various significant factors for predicting the Bitcoin price with the highest accuracy is essential. Hence, the current paper presents several Bitcoin price prediction models based on Convolutional Neural Network (CNN) and Long-Short-Term Memory (LSTM) using market sentiment and multiple feature extraction. In the proposed models, several parameters, including Twitter data, news headlines, news content, Google Trends, Bitcoin-based stock, and finance, are employed based on deep learning to make a more accurate prediction. Besides, the proposed model analyzes the Valence Aware Dictionary and Sentiment Reasoner (VADER) sentiments to examine the latest news of the market and cryptocurrencies. According to the various inputs and analyses of this study, several effective feature selection methods, including mutual information regression, Linear Regression, correlation-based, and a combination of the feature selection models, are exploited to predict the price of Bitcoin. Finally, a careful comparison is made between the proposed models in terms of some performance criteria like Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Median Absolute Error (MedAE), and coefficient of determination (R 2 ). The obtained results indicate that the proposed hybrid model based on sentiments analysis and combined feature selection with MSE value of 0.001 and R 2 value of 0.98 provides better estimations with more minor errors regarding Bitcoin price. This proposed model can also be employed as an individual assistant for more informed trading decisions associated with Bitcoin.
This study examines whether Islamic gold-backed cryptocurrencies (Onegram and X8X) provide any diversification benefits to the Islamic investors of Indonesia. We study the co-movements between return and volatility of cryptocurrencies and Indonesian Islamic equity indices during the pre-COVID-19 and COVID-19 periods. We employ Multivariate Generalized Autoregressive Conditional Heteroscedastic-Dynamic Conditional Correlation (M-GARCH-DCC) and Continuous Wavelet Transforms (CWT) for this study. We find that the COVID-19 crisis enhanced the spillover effect among the Islamic gold-backed cryptocurrencies and Islamic equities. We also provide evidence that Indonesian investors may invest in cryptocurrencies to minimize the equity sector risks during the pandemic. Our results bear significant implications for portfolio diversification strategies for Indonesian investors.
The traditional identification method of the digital bond trading contract system is single chain identification. Due to a large number of digital bond trading users, single chain identification will affect the performance of the system in the trading process. Therefore, we aim to propose a digital bond trading contract system based on blockchain technology and study the system architecture. In this paper, the architecture of the bond trading system is optimized by using the technology of blockchain, and the software architecture is developed by using the technology of blockchain. Through the performance test of the system, the advantages of the system architecture in practical application are verified. Firstly, the overall hardware architecture of the system is designed, and the internal structure of the controller in the control layer is redeployed. Combining the Mork tree and Patricia tree, the data structure based on blockchain and the block header data structure of the transaction contract system are optimized. By analyzing the operation process of the smart contract, the process of the smart contract consensus algorithm is optimized. The system performance test results show that the performance of the designed system in system transaction throughput, transaction delay, and system security is better than the traditional system, which verifies the effectiveness and reliability of the designed system.