Bitcoin Research Articles

Cryptocurrency Market Volatility and Forecasting: A Comparative Analysis of Modern Machine Learning Models for Cryptocurrencies Predicting Accuracy

Cryptocurrency (CRP) has grown in popularity over the last decade. Since there is no central body to control the Bitcoin (BTC) markets, they are extremely volatile. However, several similar variables that cause price volatility in traditional markets also affect cryptocurrencies. Several bubble phases have taken place in BTC prices, mostly during the years 2013 and 2017. Other digital currencies of primary importance, such as Ethereum and Litecoin, also exhibited several bubble phases. Among traditional methods of analysis for this volatile market, only a small number of studies focused on Machine Learning (ML) techniques. The present study objective is to get an in-depth knowledge of the time series properties of CRP data and combine volatility models with ML models. In the hybrid method, we first apply the Nonlinear Generalized Autoregressive Conditional Heteroskedasticity (NGARCH) model with asymmetric distribution to calculate standardized returns, then forecast the UP and DOWN movement of standardized returns through ML models such as Logistic Regression (LR), Linear Discrimination Analysis (LDA), Quadratic Discrimination Analysis (QDA), Artificial Neural Networks (ANNs), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). The findings show that the proposed hybrid approach of time series models and ML accurately predicts prices; specifically, the KNN model reveals that the scheme can be applicable to CRP market prediction. It is deduced that ML methods combined with volatility models have the tendency to better forecast this volatile market.

Hourly Asymmetric Multifractality and Dynamic Efficiency in Cryptocurrency Markets: The Effects of COVID‐19 and Russia–Ukraine Tension

ABSTRACTThis paper examines the hourly downward/upward multifractality and dynamic efficiency of four cryptocurrencies—Bitcoin (BTC), Ethereum (ETH), Ripple (XRP), and Litecoin (LTC)— before and during the COVID‐19 pandemic, and during the Russia–Ukraine tension. Using the asymmetric multifractal detrended fluctuation analysis method, the results show significant asymmetric multifractality in all series, which intensifies for BTC only throughout the COVID‐19 crisis and narrows for ETH, XRP, and LTC. Moreover, we show that cryptocurrency markets are more inefficient during the upward (downward) trend and before (during) the COVID‐19 crisis. LTC is the least inefficient market pre COVID‐19, whereas XRP is the least inefficient during the pandemic crisis. The results show evidence of excessive asymmetric multifractality for all four crypto markets. Before the COVID‐19 crisis, positive values of excess asymmetry in multifractality have been identified for BTC and LTC markets, whereas the excess asymmetry values were negative for ETH and XRP markets. BTC and ETH markets showed wider multifractality fluctuations compared to LTC and XRP, indicating a stronger reaction to the war's impact.

Comparative Research on Cryptocurrency Efficiency: An Objective Analysis of Key Metrics

Cryptocurrencies have introduced a transformative paradigm in financial technology, challenging traditional financial structures and creating novel transactional frameworks. With the rapid expansion of the cryptocurrency market, the need for objective assessment and comparative analysis of leading digital assets has become increasingly pertinent. This study presents a detailed, data-driven evaluation of five prominent cryptocurrencies: Bitcoin (BTC), Ethereum (ETH), Tether (USDT), USD Coin, and Lido Staked Ether (STETH). Drawing on an extensive dataset sourced from IntoTheBlock, a leading platform for cryptocurrency analytics, we assess these cryptocurrencies based on selected efficiency indicators. Our research methodology encompasses a systematic exploration of financial and network metrics, including market capitalization, volatility, daily active addresses, and transaction statistics. The results provide nuanced insights into the relative performance of these assets, identifying Bitcoin as the most efficient based on the selected criteria. This work emphasizes the significance of empirical, data-centric methodologies, eschewing subjective judgments, to deliver actionable insights for investors, policymakers, and scholars in the domain of decentralized finance.

Inter- and intra-connectedness between energy, gold, Bitcoin, and Gulf Cooperation Council stock markets: New evidence from various financial crises

This study analyzes the inter-dependence of the oil, gold, Bitcoin (BTC), and Gulf Cooperation Council stock markets during the recent Russia–Ukraine and Israel–Palestine conflicts. The study found that these markets were less inter-connected during oil battles and the Russia–Ukraine conflict but more inter-connected during the COVID-19 crisis. Findings indicated that Oman, Kuwait, gold, and Qatar are the most significant spillover receivers, whereas the United Arab Emirates (UAE), Kingdom of Saudi Arabia, and West Texas Intermediate are the primary risk spillover transmitters in the Israel–Palestine conflict. Additionally, BTC and the UAE are significant transmitters, whereas Kuwait and Qatar are the highest-risk spillover receivers in the Russia–Ukraine war. Portfolio estimates revealed that gold, BTC, and/or oil are useful in various equity markets for portfolio diversification and hedging under different market conditions and time horizons. These data can guide managers in portfolio construction and risk diversification.

Implementation of Recurrent Neural Network Gated Recurrent Unit (GRU) Model for Predicting Top-Tier Bitcoin

Cryptocurrency investments are becoming increasingly popular due to their potential as digital assets, though high price volatility poses significant challenges for investment decision-making. This study employs the Gated Recurrent Unit (GRU) model to forecast the closing prices of five prominent cryptocurrencies: Bitcoin (BTC), Ethereum (ETH), Ripple (XRP), Binance Coin (BNB), and Dogecoin (DOGE), using historical data from Yahoo Finance spanning 2019 to 2024. The model's performance was assessed using evaluation metrics, including Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). The results demonstrate that BNB achieved the best performance, with a MAPE of 2.38% and RMSE of 17.03, followed by ETH and XRP, which recorded MAPEs of 2.51% and 2.64%, respectively. BTC exhibited the highest RMSE at 2280.73, highlighting its significant price volatility, while DOGE had the lowest RMSE at 0.01, despite recording the highest MAPE at 4.11%. Forecasts for the next six periods indicate that BTC and ETH are likely to experience gradual price increases, XRP and BNB are expected to stabilize, and DOGE will remain relatively stable with low volatility. The study concludes that the GRU model is effective for cryptocurrency price forecasting, but integrating it with fundamental and technical analysis could further enhance accuracy and support more informed investment decisions.

Fake Product Identification using Blockchain

Abstract: In recent-years, blockchain has received increasing attention and numerous applications have emerged from this technology. A renowned Blockchain application is the cryptocurrency Bitcoin, that has not only been effectively solving the double-spending problem but also it can confirm the legitimacy of transactional records without relying on a centralized system to do so. Therefore, any application using Blockchain technology as the base architecture ensures that the contents of its data are tamper-proof. This paper uses the decentralized Blockchain technology approach to ensure that consumers do not fully rely on the merchants to determine if products are genuine. We describe a decentralized Blockchain system with products anticounterfeiting, in that way manufacturers can use this system to provide genuine products without having to manage directoperated stores, which can significantly reduce the cost of product quality assurance

Temporal Attention-Enhanced Stacking Networks: Revolutionizing Multi-Step Bitcoin Forecasting

This study presents a novel methodology for multi-step Bitcoin (BTC) price prediction by combining advanced stacking-based architectures with temporal attention mechanisms. The proposed Temporal Attention-Enhanced Stacking Network (TAESN) integrates the complementary strengths of diverse machine learning algorithms while emphasizing critical temporal features, leading to substantial improvements in forecasting accuracy over traditional methods. Comprehensive experimentation and robust evaluation validate the superior performance of TAESN across various BTC prediction horizons. Additionally, the model not only demonstrates enhanced predictive accuracy but also offers interpretable insights into the temporal dynamics underlying cryptocurrency markets, contributing to both practical forecasting applications and theoretical understanding of market behavior.

Predicting bitcoin cryptocurrency price behavior based on ARIMA and NNAR modelling

The development of models to predict the behavior of the Bitcoin cryptocurrency, using a public database (Yahoo! Finance) to predict price trends. The models used were ARIMA and NNAR with the validation of the models being carried out based on the daily closing values of the asset. Both models did not differ significantly, however the adjusted model NNAR (2.2) had a slightly better fit to the original data series, presenting an MPE (Mean Percentage Error) of -0.102.

Seeing Beyond Noise: Improving Cryptocurrency Forecasting with Linear Bias Correction

Cryptocurrency is recognized as a leading digital currency by its peer-to-peer transfer capabilities and secure features. Accurately forecasting cryptocurrency price trends holds substantial significance for investors and traders, as they inform critical decisions regarding the acquisition, divestment, or retention of cryptocurrencies, guided by expectations of value, risk assessment, and potential returns. This study also aims to identify a resourceful technique to efficiently forecast prices of cryptocurrencies such as Bitcoin (BTC), Binance (BNB), Ripple (XRP), and Tether (USDT) using optimal data-driven models (LSTM, GRU, and BiLSTM models) using bias correction. The proposed methodology includes collecting cryptocurrency data and precious metal data from Coindesk and BullionVault, respectively, and then finding the optimal model input combination for each cryptocurrency by lag adjustment and correlating feature selection. Hyperparameter tuning was performed by trial-and-error technique, and an early stopping function was applied to minimize time and space complexity. Bias correction (BC) is applied to model-forecasted price trends to reduce errors in evaluation and to enhance accuracy by adjusting model outputs to reduce prediction bias, providing a refined alternative to traditional unadjusted deep learning methods. GRU-BC outperformed other models in forecasting Bitcoin (with MAE 25.291, RMSE 31.266, MAPE 2.999) and USDT (with MAE 0.0006, RMSE 0.0012, MAPE 0.0622) price trends, while BiLSTM-BC was superior in predicting XRP (with MAE 0.0129, RMSE 0.0171, MAPE 2.9013) and BNB (with MAE 2.2759, RMSE 2.8357, MAPE 1.9785) market price flow.

Cross-market volatility dynamics in crypto and traditional financial instruments: quantifying the spillover effect

PurposeThis paper examines the volatility spillover effects from traditional financial assets to cryptocurrency markets and vice versa. It aims to provide insights into the dynamic interconnectedness of these markets.Design/methodology/approachThis paper employs the time-varying parameter vector autoregression technique to examine the volatility spillover among the crypto markets (across leading cryptocurrencies such as Bitcoin (BTC), USD Tether, NEAR Protocol (NEAR), Immutable and Dogecoin) and traditional financial instruments (Treasury Bills (TBILL) and Volatility Index).FindingsThe results reveal significant bidirectional volatility spillovers between cryptocurrencies and traditional financial assets. NEAR and BTC act as a major transmitter of volatility, both influencing others significantly (71.63 and 68.17%, respectively) and being influenced by others (54.74 and 62.3%, respectively). TBILL and Grayscale Bitcoin Trust ETF are the largest net receivers of volatility, indicating a higher dependency on other assets’ volatility.Practical implicationsUnderstanding the volatility spillover dynamics can aid investors in portfolio diversification and risk management. The findings provide actionable insights for constructing portfolios that include both cryptocurrencies and traditional financial assets, allowing for more informed investment decisions under volatile market conditions.Originality/valueThis paper contributes to the literature by analyzing volatility spillovers among traditional financial markets and various major cryptocurrencies. It offers a framework for assessing how shocks in one market or cryptocurrency can propagate to others, thereby enhancing the understanding of interconnectedness between markets. This understanding improves our ability to risk manage modern portfolios, which increasingly include significant alternative assets like cryptocurrencies.

Forecasting Cryptocurrency Market Movements Based on Bitcoin, Ethereum, and Ripple Returns

Cryptocurrency has transformed from a niche interest to a significant investment domain, attracting diverse investors globally. However, the cryptocurrency market is marked by extreme price volatility and risk, particularly for major digital currencies like Bitcoin (BTC), Ethereum (ETH), and Ripple (XRP). This analysis dives deeply into the historical behavior of these cryptocurrencies, examining their volatility, returns, interdependencies, and potential predictability using advancedmodeling approaches.

Decrypting Metaverse crypto Market: A nonlinear analysis of investor sentiment

This study aims to investigate the role of investor sentiment in the emerging metaverse market, a novel entrepreneurship model. Empirical analyses are conducted through various causality tests to reveal the predictive power of investor sentiment on the price developments of the metaverse market. The Nonlinear Granger causality test indicates causal effects running from BTC (Bitcoin), GT (Google Trend), and FGI (Fear-Greed Index) to MVI (Metaverse Index). Further examination of these interactions through MS-VAR analysis reveals that under bear market regimes, both investor sentiment proxies (GT and FGI) and BTC have a statistically significant causal effect on the returns of MVI. This finding suggests that metaverse crypto market returns are substantially influenced by investor sentiment during periods of anxiety and turmoil, evident in steep bear markets, rather than during periods of tranquility and euphoria characteristic of bull markets. The results of the time-varying approach confirm this finding by indicating spikes in causal effects towards the end of 2021, during which a severe crash in cryptocurrency markets occurred. Overall, the causal links during market downturns may stem from the fear of missing out (FOMO) in retail investors, who mainly dominate the sentimental factors utilized in this study.

Chaos in Bitcoin Cryptocurrency Metrics: Analysis and Forecasts

AbstractCryptocurrencies, particularly Bitcoin have attracted a lot of attention in the last decades of humanity. Analyzing cryptocurrencies algorithmic differences, chaotic behavior and self-similarity in cryptocurrency metrics might give significant insights for identifying risks and opportunities. Determining the degree of chaos in crypto metrics is critical for understanding complexity, improving prediction capabilities, and supporting decision-making. This study focuses on the analysis of chaos and self-similarity in Bitcoin dynamics for predictability perspective. Return, rate of return and volume quantities in different scales are analyzed with using rescaled range method to reveal the degree of self-similarity. Hurst parameter extracts a comprehensive summary providing information on how current values depend on previous ones to reveal any persistence in Bitcoin metrics. Daily rate of return and return give Hurst degree around 0.64 while they are in between 0.52–0.55 for minutely and hourly based prices. However, an increasing persistence is observed with the increasing time window. Although the largest Lyapunov exponents stay in the positive region for prices and returns of Bitcoin, they are approximately zero for inspected statistics. Periodic characteristics of Bitcoin are also investigated to reveal any dependencies on halving mechanism of Bitcoin. Detailed self-similarity analysis on specific periods shows that bull and bear market seasons don’t make any significant effect on the degree of Hurst parameter. Due to nonlinear and unpredictable characteristics of Bitcoin metrics, distribution fittings are applied to characterize BTC return and rate of return. While Wakeby distribution gives best fitting for daily return, Cauchy distribution gives best for hourly returns.

Comparison of Triple Exponential Smoothing and ARIMA in Predicting Cryptocurrency Prices

Cryptocurrency has emerged as a prominent digital asset over the past decade, but its high price volatility presents significant challenges for investors. This study evaluates and compares the effectiveness of the Triple Exponential Smoothing (TES) and Autoregressive Integrated Moving Average (ARIMA) methods in forecasting the prices of five major cryptocurrencies: Bitcoin (BTC), Ethereum (ETH), Binance Coin (BNB), Solana (SOL), and Ripple (XRP). TES models trends and seasonality in time series data, while ARIMA captures autoregressive patterns and moving averages. The dataset is split into 80% for training and 20% for testing, with performance evaluated using Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE). TES outperforms ARIMA in predicting Bitcoin and Binance Coin, achieving MAPE values of 10.38% and 13.81%, and RMSE values of 3,985.55 and 41.28, respectively. However, ARIMA shows better performance for Ethereum, Solana, and Ripple, with MAPE ranging from 8.78% to 32.84% and RMSE between 0.08 and 204.59. Notably, Ethereum has the lowest MAPE at 8.78%, while Ripple exhibits the smallest RMSE at 0.08. These findings suggest that TES is more suitable for cryptocurrencies with relatively stable price patterns, while ARIMA is better adapted to forecasting highly volatile assets. This research underscores the importance of selecting forecasting models based on the specific characteristics of each cryptocurrency

Bitcoin Price Bubbles and The Factors Driving Bitcoin Price Formation

The Bitcoin, one of the most discussed event of recent times, is the first cryptocurrency to be released. Bitcoin has the biggest market capitalization in the cryptocurrencies, and it is a decentralized payment tool that cannot be controlled by any government institution. Cryptocurrencies operate on top of a decentralized network, recording and verifying transactions using a technology called Blockchain. Many bubble price formations occurred in financial markets throughout history. Cryptocurrency markets are prone to manipulation because they are not connected to any center. This study aims to to investigate the buble formations in Bitcoin (BTC) US Dollar price for the period of 11 December 2017 - 31 July 2023, and also to determine the main financial variables affecting Bitcoin prices. ARDL Bounds test proves cointegration between Bitcoin price and dependent variables. Error Correction Model determines positive connection between BTC and Nasdaq100 index. A daily change in Nasdaq100 index leads to a 0.58% increase in BTC price. Model captures also negative relationship between Volatility Index, USD Index and BTC price. No long-term relationship emerges in the results. In the long run, unique and different variables shape BTC price formation.

Cryptocurrencies Price Prediction Using Deep Learning Models (Gated Recurrent Unit And Recurrent Neural Network))

Background: With their volatile prices, cryptocurrencies have become valuable assets in the financial market. Predicting cryptocurrency prices accurately is essential for making well-informed investment decisions. Time series prediction models, like Gated Recurrent Unit (GRU) and Recurrent Neural Networks (RNN), are popular tools for financial data forecasting because they can capture sequential dependencies in data. Aim: This study aims to predict the average monthly closing prices of five major cryptocurrencies—Bitcoin (BTC), Ethereum (ETH), Binance Coin (BNB), Litecoin (LTC), and Ripple (XRP)—using GRU and RNN models and evaluate their performance in forecasting these prices. Method: Time series input sequences were produced and historical price data for the chosen cryptocurrencies were preprocessed using Min-Max Scaling. This data was divided into training and test sets, and it was used to train both the GRU and RNN models. The Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) were used to assess the performance of the model. Results: For the majority of cryptocurrencies, the RNN model exhibited better predicted accuracy and consistently outperformed the GRU model. For instance, the RMSE for Ripple was 0.06 for the RNN model and 0.09 for GRU. In a similar vein, the RNN model outperformed the GRU model with a MAPE of 12.97% for Ethereum. These results imply that RNN models are more suitable for financial forecasting in this sector, as they yield more accurate predictions for cryptocurrency values.

Sustainable energy practices and cryptocurrency market behavior

We examine the effects of energy usage on the return, volatility and jump processes in the Bitcoin (BTC) and Ethereum (ETH) markets. Our main finding indicates that while BTC returns respond significantly to changes in electricity consumption, the effect of electricity consumption on ETH returns is negligible. We attribute this discrepancy to BTC's relative energy inefficiency, which contrasts with ETH's commitment to transitioning to a more energy-efficient mining protocol over our sample period. Additionally, we show that the effect of electricity consumption on cryptocurrencies is mitigated by media coverage and policy uncertainty regarding the state of the economy, environment, and cryptocurrency markets. Our results suggest that when trading cryptocurrencies, investors consider their relative energy efficiency and price electricity consumption differently, highlighting the influence of the transition towards more sustainable energy practices on investor preferences and investment decisions in cryptocurrency markets.

Predict the Trend of Indonesian People's Interest in Bitcoin Facing the 2024 Bitcoin Halving Using a Forecasting Algorithm

Cryptocurrency Bitcoin is one of the largest investment crypto assets throughout the world with a total market capitalization of 1.35 trillion US Dollars. Bitcoin was created by Satoshi Nakamoto in 2009 with a decentralized blockchain system. Indonesia is still ranked 7th in the world in cryptocurrency adoption, which means Indonesia is still behind other countries. The inhibiting factors are poor government regulations and a lack of public education platforms regarding this new cryptocurrency technology. This research aims to analyze and predict trends in Indonesian people's interest in bitcoin in the context of the 2024 bitcoin halving, taking Google Trends data and then predicting it using a double exponential forecasting algorithm. Related data was collected to analyze community interest patterns using the KDD (Knowledge Discovery in Database) method. Searches with the keyword "bitcoin" reached the day of the 2024 bitcoin halving on April 19, 2024. From the dataset obtained from the 2014-2024 period with a total of 121 records, using the double exponential 29 forecasting algorithm produces test and train RMSE values of 7,184 and 14,907. Meanwhile, the train and test MAPE values are 0.313 and 0.861. The model that has been created is then implemented using the Python Stremlit library so that web-based analysis can be carried out. The predicted peak point value in 09-2024 is 48.5 and the lowest point in 08-2025 is 17.9. It is hoped that this trend analysis can help develop the adoption of crypto assets, especially bitcoin, to educate the public about the importance of bitcoin as a future investment asset, and the government needs to play a role in making crypto adoption easier in Indonesia.

Investigation of Fluctuations in Cryptocurrency Transactions with Sentiment Analysis

This study investigates public sentiment about popular cryptocurrencies listed on crypto exchanges in Turkey, using comments shared on social media platforms and online forums. The research seeks to enhance the existing body of knowledge by overcoming the shortcomings of sentiment analysis studies focused on Turkish texts. Data collected from social media and online forums were examined with sentiment analysis techniques. A total of 607,592 comments were analyzed, of which 89,986 were classified as negative, 72,655 as positive, and 444,951 as neutral. For binary classification, 89,986 negative and 72,655 positive examples were selected and machine-learning models were trained and tested on 162,641 examples. The study's methodology includes an in-depth examination of sentiment analysis results obtained using machine learning classifiers. The findings show how various cryptocurrencies are perceived on different social media platforms. For instance, BTC (Bitcoin) is generally perceived negatively on Investing.com and Telegram, while ETH (Ethereum) generally displays more negative views. These results help investors understand their perceptions and market expectations towards cryptocurrencies. This study deepens the role of social media sentiment analysis in cryptocurrency markets, contributing to the development of new methods and approaches for future research.

WITHDRAWN: Mimicking crypto portfolios in sustainable investment

In this paper, considering the difference in the energy demand level, we utilize the daily pricing data from 10/01/2019 to 06/30/2023 to construct mimicking crypto portfolios with 12 clean cryptocurrencies to replace the dirty cryptocurrency, Bitcoin (BTC). With a monthly rebalancing strategy, the mimicking portfolio closely matches the exposures to the risk factors of the BTC but with fewer specific risks. Furthermore, relying on the bivariate dynamic conditional correlation (DCC-) GARCH model, we compare the hedging capability of BTC and the corresponding mimicking crypto portfolio against movements of returns of sustainable assets. The empirical results show that the mimicking crypto portfolio provides ESG investors with a cheaper hedge tool of higher hedge effectiveness compared to the BTC. Moreover, we find that the mimicking crypto portfolio can act as a strong safe haven for the S&P Global Clean Energy Index and S&P Latin America Emerging LargeMidCap ESG Index during periods of market stress. Therefore, the mimicking crypto portfolio is a more attractive option for ESG investors due to its superior hedging efficiency and the added environmental advantages.