MangiReddiHemanth, MunipalliSasi Chandra, VaddeRaviteja, R. Sumathi · 5 authors
The major aim of this work is to uncover the accuracy of the Bitcoin price in any fiat/flat currency that can be predicted in advance. Bitcoin is a form of cryptocurrency and is now one of the most popular types of investments in the stock market. And bitcoin is the only form of cryptocurrency that has been on the rise in the last few years, and sometimes a sudden collapse without knowing the impact behind it in the stock market. To utilize the long short-term memory for predicting the bitcoin value in advance. Many researchers used RNN for this bitcoin prediction and observed that it lacks in consistency, to overcome this issue LSTM and ARIMA are used to ensure the accuracy and yields better prediction in terms of time series and proves that it is superior to existing state of art techniques.
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.
Being a revolutionary form of financial instrument, Bitcoin's rapid price fluctuations inevitably prompt the query of whether its price can be predicted. This is a crucial question, particularly in light of Bitcoin's brief history and the ease with several factors may have an impact on its price. This study investigates the direction prediction of Bitcoins volatility using internal, blockchain data, such as the past prices of Bitcoin and blockchain’s characteristics. Convolutional neural networks (CNN), among other methodologies, have lately been used for automatic feature selection and market forecasting. In this research, we propose a CNN based framework using blockchain features for predicting the direction of Bitcoins volatility from a set of data from various sources. The proposed methodology has been used to predict the next day's direction of movement for Bitcoin on a variety of different variables. The evaluation displays a significant accuracy of 57% in prediction's performance and a mean absolute error (loss) of 43%, a result that suggests CNN's framework significant when predicting Bitcoin's volatility. This research proposes an interpretative approach to derive feature importance, which represents the degree to which an input feature may discriminate between distinct classes, in order to better understand how these networks make their final selections. Moreover, we found that the blockchain’s characteristics that had an impact in the performance of the CNN algorithm were the total value of all transaction outputs per day, the miner’s revenue divided by the number of transactions, the total estimated value in USD of transactions, the miner’s revenue and the total number of confirmed transactions per day.
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.
Cryptocurrency has gained its popularity in recent years. Due to enormous profitability potential, many investors and researchers alike have taken an interest in this domain. There is a lot of data in the cryptocurrency market that has to be analysed to make the right choices quickly when trading. Many have tried to automate the trading process by utilizing various prediction models and reinforcement learning to further streamline the trading process. It is therefore important to collect and summarize current state of the art technologies that investors and researchers use to predict and automate the cryptocurrency trading process. This paper provides a repository of knowledge to find out what other researchers have done by covering more than 13 different machine learning methods and several hybrid methods. This paper is the initial research step to try to come up with a new state-of-the-art approach to programmatic trading by determining a method that can be researched further.
Ensemble learning is a methodology that entails integrating a number of inefficient entities to achieve significantly improved performance. Boosting is a significant category of ensemble learning that involves the consecutive aggregate input of weak learners. The benefits of boosting approaches in processing tabular data with a significant quantity of information and resistance to overfitting can be very useful in estimating the market value of digital currency or cryptocurrency. The goal of this work is to examine and comprehend the capabilities of major boosting techniques such as XGBoost, AdaBoost, and CatBoost in cryptocurrency forecasting. The work examines the long-term forecasts of two major cryptocurrencies, Bitcoin and Ripple, for this purpose. The results indicate that AdaBoost and XGBoost have comparable predicting efficiency, followed by CatBoost. This implies that AdaBoost’s simpler boosting strategy is effective at achieving outcomes that are comparable to those of more recent boosting algorithms like XGBoost and CatBoost. The study has emphasized the similarities in achieving the best cryptocurrency prediction outcomes from each model. According to the research, a more straightforward boosting tactic is just as effective as or even more effective than the other most recent boosting strategies.
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.
Forecasting economic goods market recoveries is challenging due to the volatility and uncertainty of the market's structure. Since the introduction of machine learning and increased computer power, programmable forecasting approaches have been found to be particularly effective in predicting stock values. Random Decision Forest, K - Nearest Neighbors, and Linear Regression were among the natural processing techniques employed in this study to forecast the costs of popular crypto currencies like Bit coin and Ethereum over the next few years. The model is given financial data on stock prices from the start of the day to the end of the day. Bitcoin's value may or may not improve in the future because it has been on the market for a decade. Ethereum was created in 2015 and is now the second most popular crypto currency on the market. The value of Ethereum is nearly comparable to that of Bit coin. After a few years, it is doubtful whether bit coin will be available on the market. As a result, buyers seek forecasts in order to invest in the right crypto currency and profit from it. The user can use this forecast to anticipate the future of both crypto currency prices. To assess the value of crypto currencies, we used three forecasted analytic techniques, and we can compare the accuracy of the three algorithms to see which one is the best.
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.
P. Chandra Sekhar, M Padmaja, Biswajit Sarangi, Aditya Aditya
Digital currency arose because of progress in financial technology and created opportunities for profitable cryptocurrency investment. The high instability of Bitcoin made cryptocurrency trading so worthwhile in the last few years. Investors are looking for a secure mechanism to forecast the cryptocurrency price fluctuations in the market that will fuel their investment strategies. The algorithms such as random forest, Bayesian neural network, or long-short-term-memory (LSTM) neural network analyze the price fluctuations of the cryptocurrencies through the historical data and attain high precision. This paper analyzed a few shortcomings of the LSTM network and explored the vital parameters to overcome them. This paper employed the XGBoost algorithm to predict cryptocurrency prices better and found a better mean value deviation error than LSTM.
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.
Iqra Sadia, Atif Mahmood, Miss Laiha Mat Kiah, Saaidal Razalli Azzuhri
The rapid growth of cryptocurrencies has gained much attention by media, investors and scholars, since it is widely used for investment purposes as an alternative to regular currencies. Therefore the intelligent management and under-standing the characteristics of cryptocurrencies are becoming more interesting. The price of cryptocurrencies are characterized by linear and nonlinear trend, seasonality and high volatility, which increases the risk factors for investors. This study ex-periments with three different time series forecasting methods, specifically considered for Cryptocurrencies price such as Bitcoin (BTC), Ethereum (ETH), Litecoin (LTC), Monero (XMR) and Cardano (XRP), and devises a procedure to evaluate their performance. Time series data are collected and examined using descriptive statistics. In next step, the White Neural Network is used for Non-Linearity and Dickey-Fuller for nonstationary and correlation among different settings of datasets. Based on these analyses, we evaluate efficient financial forecasting models such as Autoregressive Integrated Moving Average (ARIMA), Trigonometric, Box-Cox transformation, ARMA errors, Trend and Seasonal (TBATS) and Neural Network Autoregressive (NNAR) with reference to different parameters configuration of these models. The performance is evaluated using Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) criterion and models are ranked by statistical mean and standard deviation of MAPE values. The NNAR model gives minimum MAPE of 2.823 while the minimum convergence time of 4.9835s is observed with TBATS and hence, these are ranked at top amongst other models respectively. These results underpin that neural network-based models perform equally well on both types of nonlinear and linear financial data and, thus, have the potential to improve the impact of financial transaction and cryptocurrencies price bringing more innovation in the decision making process.
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.