The rapid expansion of the non-fungible token (NFT) market has attracted many investors. However, studies on the NFT price fluctuations have been relatively limited. To date, the machine learning approach has not been used to demonstrate a specific error in NFT sale price fluctuation prediction. The aim of this study was to develop a prediction model for NFT price fluctuations using the NFT trading information obtained from OpenSea, the world’s largest NFT marketplace. We used Python programs to collect data and summarized them as: NFT information, collection information, and related account information. AdaBoost and Random Forest (RF) algorithms were employed to predict the sale price and price fluctuation of NFTs using regression and classification models, respectively. We found that the NFT related account information, especially the number of favorites and activity status of creators, confer a good predictive power to both the models. AdaBoost in the regression model had more accurate predictions, the root mean square error (RMSE) in predicting NFT sale price was 0.047. In predicting NFT sale price fluctuations, RF performed better, which the area under the curve (AUC) reached 0.956. We suggest that investors should pay more attention to the information of NFT creators. We anticipate that these prediction models will reduce the number of investment failures for the investors.
Muhammad Rafi, Qublai Khan Ali Mirza, Muhammad Izaan Sohail, Maria Aliasghar · 6 authors
A cryptocurrency is a digitized, encrypted, and decentralized virtual currency, which is impossible to counterfeit or double-spend. It is one of the very popular investment instruments and traded in blockchain based crypto exchanges on ever growing volume. It is quite volatile due to imbalance of supply and demand, government regulations, investor sentiment and above all media hype. Cryptocurrency price forecasting is an active area of research and several approaches have been proposed recently. This study proposed a price forecasting model based on three vital characteristics (i) a feature selection and weighting approach based on Mean Decrease Impurity(MDI) features. (ii) Bi-directional LSTM and (iii) with a trend preserving model bias correction (CUSUM control charts for monitoring the model performance over time) to forecast Bitcoin and Ethereum values for long and short term spans. The data for both currencies were analyzed in three different intervals: (i) April 01, 2013 to April 01, 2016 (ii) April 01, 2013 to April 01, 2017 and (iii) April 01, 2013 to December 31, 2019. Extensive series of experiments were performed and evaluated on Root Mean Square Errors (RMSE). Comparing with the prevalent forecasting models we report a new state of the art in cryptocurrency forecasting.
Lin William Cong, Pulak Ghosh, Jiasun Li, Qihong Ruan
Using proprietary data from the predominant cryptocurrency exchange in India together with the country's Household Inflation Expectations Survey, we document a significantly positive association between inflation expectations and individual cryptocurrency purchases.Higher inflation expectations are also associated with more new investors in cryptocurrencies.We investigate investment heterogeneity in multiple dimensions, and find the effect to be concentrated in Bitcoin (BTC) and Tether (USDT) trading.The results are robust after controlling for speculative demand captured by surveys of investors' expected cryptocurrency returns, and admit causal interpretations as confirmed using multiple instrumental variables.Our findings provide direct evidence that households already adopt cryptocurrencies for inflation hedging, which in turn rationalizes their high adoption in developing countries without a globally dominant currency.
Central banks may shift their international reserve holdings in order to protect themselves ex-ante against the risk of financial sanctions by fiat reserve currency issuers. For example, from 2016 to 2021, countries facing a higher risk of US sanctions increased the gold share of their reserves more than countries facing a lower risk of US sanctions. This paper explores the potential for Bitcoin to serve as an alternative hedging asset. I describe a dynamic Bayesian copula model to simulate the joint returns of Bitcoin and other reserve assets under a wide range of plausible sanctions probabilities, quantifying the extent to which varying levels of sanctions risk increase optimal gold, renminbi, and Bitcoin allocations. I conclude that sanctions risk may diminish the appeal of US Treasuries, propel broader diversification in central bank reserves, and bolster the long-run fundamental value of both cryptocurrency and gold. • The paper simulates the returns of Bitcoin and other reserve assets. • The simulations balance expected return, volatility, and sanctions risk. • In the presence of sanctions, there is no completely safe asset. • The model shows that cryptocurrency can act as a form of insurance. • Sanctions risk may propel broader diversification in central bank reserves.
Despite their popularity in recent studies, most hybrid models that exploit the advantages of both classical time series and deep learning models were conducted in univariate forecasting context. For econometric domain which exogenous factors play a crucial role, more studies in multivariate forecasting is essential and should be encouraged. Thus, contributing to hybrid multivariate forecasting literature, a hybrid model named HyBiLSTM was proposed. The algorithm began with ARIMAX GARCHX model forecasting, followed by second forecasting of model residual using Grey Wolf Optimizer based hyperparameters Bidirectional LSTM model. With residuals instead of original multivariate features, LSTM can avoid to processes each feature independently and therefore, reducing convergence complexity and execution time. The final forecasting results was compounded from both models. Three quantitative measurements, Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE), were used to evaluate the established models using the historical daily runoff social and economic based data (01/07/2019-31/12/2022). The findings showed 1) the addition of exogenous factors improved the performance of ARIMA and GARCH models; 2) BiLSTM outperformed other LSTM variants when was integrated with ARIMAX GARCHX model; 3) Using SHAP, Bitcoin price was influenced by stock price, Twitter volume, gold price, and Twitter sentiment index; and 4) structural break had significant effect on forecasting. Other than expanding the literatures regarding hybrid models in multivariate context, this study provides practical contribution for investors by analyzing the factors that the investors can use as an early warning for Bitcoin price fluctuation.
S. Pourmohammad Azizi, Chien Yi Huang, Ti An Chen, Shu Chuan Chen · 5 authors
<abstract><p>In this article, an alternate method for estimating the volatility parameter of Bitcoin is provided. Specifically, the procedure takes into account historical data. This quality is one of the most critical factors determining the Bitcoin price. The reader will notice an emphasis on historical knowledge throughout the text, with particular attention paid to detail. Following the production of a historical data set for volatility utilizing market data, we will analyze the fundamental and computed values of Bitcoin derivatives (futures), followed by implementing an inverse problem modeling method to obtain a second-order differential equation model for volatility. Because of this, we can accomplish what we set out to do. As a direct result, we will be able to achieve our objective. Following this, the differential equation of the second order will be solved by an artificial neural network that considers the dataset. In conclusion, the results achieved through the utilization of the Python software are given and contrasted with a variety of other research approaches. In addition, this method is determined with alternative ways, and the outcomes of those comparisons are shown.</p></abstract>
Karamath Ateeq, Ahmed Abdelrahim Al Zarooni, Abdur Rehman, Muhammad Adnan Khan
Researchers and investors have recently become interested in forecasting the cryptocurrency price forecasting but the most important currency can take that it’s the bitcoin exchange rate. Some researchers have aimed at leveraging the technical and financial characteristics of Bitcoin to create predictive models, while others have utilized conventional statistical methods to explain these factors. This article explores the LSTM model for forecasting the value of bitcoins using historical bitcoin price series. Predict future bitcoin prices by developing the most accurate LSTM forecasting model, building an advanced LSTM forecasting model (LSTM-BTC), and comparing past bitcoin prices. This is the second step, if looking at the end of the model, it has very high accuracy in predicting future prices. The performance of the proposed model is evaluated using five different datasets with monthly, weekly, daily, hourly, and minute-by-minute bitcoin price data with total records from January 1, 2021, to March 31, 2022. The results confirm the better forecasting accuracy of the proposed model using LSTM-BTC. The analysis includes square error MSE, RMSE, MAPE, and MAE of bitcoin price forecasting. Compared to the conventional LSTM model, the suggested LSTM-BTC model performs better. The contribution made by this research is to present a new framework for predicting the price of Bitcoin that solves the issue of choosing and evaluating input variables in LSTM without making firm data assumptions. The outcomes demonstrate its potential use in applications for industry forecasting, including different cryptocurrencies, health data, and economic time.
Thomas Conlon, Shaen Corbet, Yang Hou, Yang Hu · 5 authors
Despite frequent Blockchain splits stemming from Bitcoin, few studies have examined the determinants of Bitcoin fork returns. In this paper, we investigate the relationships between the returns of Bitcoin forks and a range of common risk factors, including Bitcoin, currency, network and equity-based factors. From a statistical perspective, we find consistent and significant associations between fork returns, their Bitcoin counterparts, and equity markets. Other common factors, such as the equity small-minus-big factor and changes in the Japanese Yen, are found to have occasional links with fork returns. From an economic perspective, Bitcoin returns are the predominant driver of fork returns, accounting for essentially all of the explained variation. These findings are confirmed using orthogonalised common factors and with an alternative methodology, quantile regression. This research broadens our understanding of Bitcoin forks, indicating that a change in blockchain protocol is insufficient to sever links with the Bitcoin parent.
This research examines the correlations between the return volatility of cryptocurrencies, global stock market indices, and the spillover effects of the COVID-19 pandemic. For this purpose, we employed a two-stage multivariate volatility exponential GARCH (EGARCH) model with an integrated dynamic conditional correlation (DCC) approach to measure the impact on the financial portfolio returns from 2019 to 2020. Moreover, we used value-at-risk (VaR) and value-at-risk measurements based on the Cornish–Fisher expansion (CFVaR). The empirical results show significant long- and short-term spillover effects. The two-stage multivariate EGARCH model’s results show that the conditional volatilities of both asset portfolios surge more after positive news and respond well to previous shocks. As a result, financial assets have low unconditional volatility and the lowest risk when there are no external interruptions. Despite the financial assets’ sensitivity to shocks, they exhibit some resistance to fluctuations in market confidence. The VaR performance comparison results with the assets portfolios differ. During the COVID-19 outbreak, the Dow (DJI) index reports VaR’s highest loss, followed by the S&P500. Conversely, the CFVaR reports negative risk results for the entire cryptocurrency portfolio during the pandemic, except for the Ethereum (ETH).
Cryptocurrencies have recently attracted considerable attention, resulting in research mainly on deep learning-based price prediction models to maximize profit. Two research approaches have been adopted. Studies adopting the first approach directly predict the future cryptocurrency price. Long short-term memory (LSTM) and gated recurrent unit (GRU), which show high performance in time-series data, are mainly used for this approach. Further, studies adopting the second approach recommend actions to investors to maximize profits, such as “Sell”, “Buy”, and “Wait.” In this approach, classification models are used and results are derived based on probabilities. However, these action recommendation models do not consider the quality of the result. For example, it is risky to accept the result when the probability that the result of the action recommendation model for two classes is the correct answer is approximately 51%. To solve this problem, we recommend a method for adjusting the result of the action recommendation model based on Twitter sentiment analysis. The experimental results show that the proposed adjustment method improves the performance by approximately 3% compared to the conventional methods and are statistically validated.
Fabian E. Eska, Yanghua Shi, Erik Theissen, Marliese Uhrig‐Homburg
This paper examines the impact of cryptocurrency design features on their return volatility. We compile a sample of 58 cryptocurrencies, adopt the taxonomy of design features proposed by Eska et al. (2022), and estimate LASSO regressions. We document that older cryptocurrencies tend to be less volatile. Networks with mandatory transaction fees, cryptocurrencies based on (delegated) Proof-of-Stake, and those developed by private for-profit entities tend to be more volatile. Furthermore, we provide evidence that networks passing transaction fees and/or tips on to verifiers are associated with higher volatility levels.
This paper investigates the price discovery relationships between FTT Token, issued by the cryptocurrency exchange FTX, and a set of assets and liabilities held by FTX amid a period of catastrophic financial decline by applying novel information flow measurement techniques. Results indicate that during key phases associated with the collapse of FTX, FTT Token had an informational lead over multiple assets, including cryptocurrencies such as Ethereum. Furthermore, we identify significant interactions between the FTT Token and both Robinhood shares and the token Serum, raising concerns about the direct influence of permissionless, technically valueless tokens on other assets and the potential challenges to market stability and investor protection. Our findings underscore the need for stronger policy-making, regulatory, and ethical considerations in cryptocurrency markets.
Hasib Shamshad, Fasee Ullah, Asad Ullah, Victor R. Kebande · 6 authors
The digital market trend is rapidly expanding due to key characteristics like decentralization, accessibility, and market diversity enabled by blockchain technology. This study proposes a Predictive Analytics System to provide simplified reporting for the three most popular cryptocurrencies with varying digits, namely ADA Cardano, Ethereum, and Binance coin, for ten days to contribute to this emerging technology. Thus, this proposed system employs a data science-based framework and six highly advanced data-driven Machine learning and Deep learning algorithms: Support Vector Regressor, Auto-Regressive Integrated Moving Average (ARIMA), Facebook Prophet, Unidirectional LSTM, Bidirectional LSTM, Stacked LSTM. Moreover, the research experiments are repeated several times to achieve the best results by employing hyperparameter tuning of each algorithm. This involves selecting an appropriate kernel and suitable data normalization technique for SVR, determining ARIMA’s (p, d, q) values, and optimizing the loss function values, number of neurons, hidden layers, and epochs in LSTM models. For the model validation, we utilize widely used evaluation techniques: Mean Absolute Error, Root Mean Squared Error, Mean Absolute Percentage Error, and R-squared. Results demonstrate that ARIMA outperforms the other models in all cases, accurately projecting the price variability within the actual price range. Conversely, Facebook Prophet exhibits good performance to some extent. The paper suggests that the ARIMA technique offers practical implications for market analysts, enabling them to make well-informed decisions based on accurate price projections.
Abstract Much of the media focus surrounding Bitcoin (BTC) has been on the ‘E’ (environmental) element of the ESG investing approach. Given the amount of electricity consumed by BTC mining, and the resulting large carbon emissions, BTC has faced substantial criticism of its overly negative environmental impact, which is critically reviewed in this article. This one‐sided discussion, however, ignores the ‘S’ (social) and ‘G’ (governance) elements entirely. To remedy that, we explore BTC's positive impact on the ‘S’ (user satisfaction, data protection and privacy, human rights, and criminal activity), and ‘G’ (accounting integrity and transparency, compensation, and principles of good governance) components.
Muhammad Anas, Syed Jawad Hussain Shahzad, Larisa Yarovaya
Abstract As the crypto-asset ecosystem matures, the use of high-frequency data has become increasingly common in decentralized finance literature. Using bibliometric analysis, we characterize the existing cryptocurrency literature that employs high-frequency data. We highlighted the most influential authors, articles, and journals based on 189 articles from the Scopus database from 2015 to 2022. This approach enables us to identify emerging trends and research hotspots with the aid of co-citation and cartographic analyses. It shows knowledge expansion through authors’ collaboration in cryptocurrency research with co-authorship analysis. We identify four major streams of research: (i) return prediction and measurement of cryptocurrency volatility, (ii) (in)efficiency of cryptocurrencies, (iii) price dynamics and bubbles in cryptocurrencies, and (iv) the diversification, safe haven, and hedging properties of Bitcoin. We conclude that highly traded cryptocurrencies’ investment features and economic outcomes are analyzed predominantly on a tick-by-tick basis. This study also provides recommendations for future studies.