Search Results (192)

This study proposes a hybrid approach to analyze and forecast non-stationary financial time series by combining statistical models with deep neural networks. A model is introduced that integrates three key components: the Generalized Autoregressive Score (GAS) model, which captures volatility dynamics; an attention mechanism (ATT), which identifies the most relevant features within the sequence; and a Long Short-Term Memory (LSTM) neural network, which receives the outputs of the previous modules to generate price forecasts. This architecture is referred to as GAS-ATT-LSTM. Both unidirectional and bidirectional variants were evaluated using real financial data from the Nasdaq Composite Index, Invesco QQQ Trust, ProShares UltraPro QQQ, Bitcoin, and gold and silver futures. The proposed model’s performance was compared against five benchmark architectures: LSTM Bidirectional, GARCH-LSTM Bidirectional, ATT-LSTM, GAS-LSTM, and GAS-LSTM Bidirectional, under sliding windows of 3, 5, and 7 days. The results show that GAS-ATT-LSTM, particularly in its bidirectional form, consistently outperforms the benchmark models across most assets and forecasting horizons. It stands out for its adaptability to varying volatility levels and temporal structures, achieving significant improvements in both accuracy and stability. These findings confirm the effectiveness of the proposed hybrid model as a robust tool for forecasting complex financial time series. Full article

This study aims to analyze the impact of the U.S. Federal Reserve System’s monetary policy on major cryptocurrencies. Specifically, it explores whether the effects differ between volatile cryptocurrencies, such as Bitcoin and Ethereum, and the stablecoin Tether. To this end, we utilize an autoregressive distributed lag (ARDL) bounds testing approach, analyzing monthly data from January 2019 to April 2025. The empirical results indicate that the responses of volatile and stable cryptocurrencies to the Fed’s monetary policy differ. In the long term, the prices of Bitcoin and Ethereum tend to react positively to the Fed’s monetary policy changes, whereas Tether’s prices experience a negative impact. We recommend novel policy implications in this study based on these empirical findings. Full article

This paper proposes a comprehensive deep-learning framework, SentiStack, for Bitcoin price forecasting and trading strategy evaluation by integrating multimodal data sources, including market indicators, macroeconomic variables, and sentiment information extracted from financial news and social media. The model architecture is based on a Stacking-LSTM ensemble, which captures complex temporal dependencies and non-linear patterns in high-dimensional financial time series. To enhance predictive power, sentiment embeddings derived from full-text analysis using the DeepSeek language model are fused with traditional numerical features through early and late data fusion techniques. Empirical results demonstrate that the proposed model significantly outperforms baseline strategies, including Buy & Hold and Random Trading, in cumulative return and risk-adjusted performances. Feature ablation experiments further reveal the critical role of sentiment and macroeconomic inputs in improving forecasting accuracy. The sentiment-enhanced model also exhibits strong performance in identifying high-return market movements, suggesting its practical value for data-driven investment decision-making. Overall, this study highlights the importance of incorporating soft information, such as investor sentiment, alongside traditional quantitative features in financial forecasting models. Full article

This paper examines the relationship between dependence and independence alternatives in general stochastic processes and explores the duality between the true (yet unknown) stochastic process and the functional representation that fits the observed data. We demonstrate that the solution depends on its historic realizations, challenging existing theoretical frameworks that assume independence between the solution and the history of the true process. Under orthogonality conditions, we investigate parameter spaces within data-generating processes and establish conditions under which data exhibit mean-reverting, random, cyclical, history-dependent, or explosive behaviors. We validate our theoretical framework through empirical analysis of an extensive dataset comprising daily prices from the S&P500, 10-year US Treasury bonds, the EUR/USD exchange rate, Brent oil, and Bitcoin from 1 January 2002 to 1 February 2024. Our out-of-sample predictions, covering the period from 17 February 2019 to 1 February 2024, demonstrate the model’s exceptional forecasting capability, yielding correct predictions with between 73% and 92% accuracy, significantly outperforming naïve and moving average models, which only achieved 47% to 54% accuracy. Full article

Predicting the price of Bitcoin is crucial, primarily because of the market’s rapid volatility and non-linear environment. For enhanced prediction of the price of Bitcoin, this research proposed a novel interpretable hybrid technique that combines long short-term memory (LSTM) networks with convolutional neural networks (CNN). Deep variational autoencoders (VAE) are used in the stage of preprocessing to determine noticeable patterns in datasets by learning features from historical Bitcoin price data. The CNN-LSTM model additionally implies Shapley additive explanations (SHAP) to promote interpretability and clarify the role of various features. For better performance, the methodology used data cleaning, preprocessing, and effective machine-learning techniques. The hybrid CNN + LSTM model, in collaboration with VAE, obtains a mean squared Error (MSE) of 0.0002, a mean absolute error (MAE) of 0.008, and an R-squared (R²) of 0.99, based on the experimental results. These results show that the proposed model is a good financial forecast method since it effectively reflects the complex dynamics of primary changes in the price of Bitcoin. The combination of deep learning and explainable artificial intelligence improves predictive accuracy as well as transparency, thus qualifying the model as highly useful for investors and analysts. Full article

Bitcoin’s role in global finance has rapidly expanded with increasing institutional participation, prompting new questions about its linkage to macroeconomic variables. This study thoughtfully integrates a Bayesian Markov Chain Monte Carlo (MCMC) covariate selection process within homogeneous and non-homogeneous Hidden Markov Models (HMMs) to analyze 16 macroeconomic and Bitcoin-specific factors from 2016 to 2024. The proposed method integrates likelihood penalties to refine variable selection and employs a rolling-window bootstrap procedure for 1-, 5-, and 30-step-ahead forecasting. Results indicate a fundamental shift: while early Bitcoin pricing was primarily driven by technical and supply-side factors (e.g., halving cycles, trading volume), later periods exhibit stronger ties to macroeconomic indicators such as exchange rates and major stock indices. Heightened volatility aligns with significant events—including regulatory changes and institutional announcements—underscoring Bitcoin’s evolving market structure. These findings demonstrate that integrating Bayesian MCMC within a regime-switching model provides robust insights into Bitcoin’s deepening connection with traditional financial forces. Full article

This paper investigates Bitcoin’s resilience against the U.S. dollar—widely recognized as the global reserve currency—by applying a multi-method wavelet analysis framework to daily price data of Bitcoin, the USD strength index (DXY), the euro, and other assets ranging from August 2015 to June 2024. Quantitative measures—particularly the Frobenius norm of wavelet coherence and an exponential decay phase-weighting scheme—reveal that Bitcoin’s out-of-phase relationship with the dollar is lower and more sporadic than that of mainstream assets, indicating it is not tightly governed by dollar fluctuations. Even after controlling for the euro’s dominant influence in the DXY, BTC continues to show weaker coupling than mainstream assets—reinforcing the idea that it may serve as a partial hedge against dollar-driven volatility. These results support the hypothesis that Bitcoin may serve as a resilient store of value and hedge against dollar-driven market volatility, placing Bitcoin within the broader debate on global monetary frameworks. As global monetary conditions evolve, the resilience of Bitcoin (BTC) relative to the world’s leading reserve currency—the U.S. dollar—has significant implications for both investors and policymakers. Full article

This study explores integrating Bitcoin mining with lignocellulosic biorefineries to create an additional revenue stream. Profits from mining can help offset internal costs, reduce business expenses, or lower consumer prices. Using sensitivity analysis and Monte Carlo simulations, this study identifies key profitability drivers, such as electricity costs, hardware expenses, starting year, and operational time. Time emerged as an extremely sensitive factor and showed that delaying mining operations significantly raised production costs and the probability of profitable outcomes. In contrast, longer mining durations had a smaller yet sizable impact. Hardware costs, computational efficiency, and electricity prices also strongly influenced the outcomes. The majority of simulated events showed a loss. Moreover, the model showed that the marginal profitability of mining decreases over time. Nonetheless, the model demonstrated that under favourable conditions, it is possible to integrate Bitcoin mining into biorefineries and other productive ventures, thereby allowing for cost recovery using Bitcoin profits. For a biorefinery to mine Bitcoin and maximise cost recovery, it must start early, access low electricity prices, and preserve hardware capital characterised by low expenditure and high revenues. Finally, a discussion about the opportunities, risks, and regulations is highlighted. Full article

This study examines how cumulative abnormal returns (CARs, the sum of abnormal returns over a period) and volatility behave around Bitcoin halving events, focusing on whether these patterns have evolved as the cryptocurrency market matures. Halvings are periodic events defined by Bitcoin’s algorithm, during which the reward—in the form of newly issued bitcoins—paid to miners for validating network transactions is reduced, impacting miners’ profitability and potentially influencing the asset’s price due to a decreased supply. To carry out the analysis, we collected data on returns and risk for the 2012, 2016, 2020, and 2024 halving events and compared abnormal returns before and around the event, focusing on the 2020 and 2024 halvings. The results reveal significant shifts in Bitcoin’s price behavior within the event window, with an increased occurrence of abnormal returns in 2020 and 2024, alongside variations in average return, volatility, and maximum drawdown across all events. These findings suggest that Bitcoin’s returns and volatility during halvings are decreasing as the cryptocurrency market becomes more regulated and attracts greater participation from institutional investors and governments. Full article

This study investigates the multifractal behavior of four leading semiconductor stocks—Intel (INTC), Advanced Micro Devices (AMD), Nvidia (NVDA), and Broadcom (AVGO)—in relation to key financial assets, including the Dow Jones Industrial Average (DJI), the Euro–U.S. Dollar exchange rate (EUR), gold (XAU), crude oil (WTI), and Bitcoin (BTC), using Multifractal Asymmetric Detrended Cross-Correlation Analysis (MF-ADCCA). The analysis is based on daily price return time series from January 2015 to January 2025. Results reveal consistent evidence of multifractality across all asset pairs, with the generalized Hurst exponent exhibiting significant variability, indicative of complex and nonlinear stock price dynamics. Among the semiconductor stocks, NVDA and AVGO exhibit the highest levels of multifractal cross-correlation, particularly with DJI, WTI, and BTC, while AMD consistently shows the lowest, suggesting comparatively more stable behavior. Notably, cross-correlation Hurst exponents with BTC are the highest, reaching approximately 0.54 for NVDA and AMD. Conversely, pairs with EUR display long-term negative correlations, with exponents around 0.46 across all semiconductor stocks. Multifractal spectrum analysis highlights that NVDA and AVGO exhibit broader and more pronounced multifractal characteristics, largely driven by higher fluctuation intensities. Asymmetric cross-correlation analysis reveals that stocks paired with DJI show greater persistence during market downturns, whereas those paired with XAU demonstrate stronger persistence during upward trends. Analysis of multifractality sources using surrogate time series confirms the influence of fat-tailed distributions and temporal linear correlations in most asset pairs, with the exception of WTI, which shows less complex behavior. Overall, the findings underscore the utility of multifractal asymmetric cross-correlation analysis in capturing the intricate dynamics of semiconductor stocks. This approach provides valuable insights for investors and portfolio managers by accounting for the multifaceted and asset-dependent nature of stock behavior under varying market conditions. Full article

Standard correlation analysis is one of the frequently used methods in financial markets. However, this matrix can give erroneous results in the conditions of chaos, fractional systems, entropy, and complexity for the variables. In this study, we employed the time-dependent correlation matrix based on isospectral flow using the Lie group method to assess the price of Bitcoin and gold from 19 July 2010 to 31 December 2024. Firstly, we showed that the variables have a chaotic and fractional structure. Lo’s rescaled range (R/S) and the Mandelbrot–Wallis method were used to determine fractionality and long-term dependence. We estimated and tested the d parameter using GPH and Phillips’ estimators. Renyi, Shannon, Tsallis, and HCT tests determined entropy. The KSC determined the evidence of the complexity of the variables. Hurst exponents determined mean reversion, chaos, and Brownian motion. Largest Lyapunov and Hurst exponents and entropy methods and KSC found evidence of chaos, mean reversion, Brownian motion, entropy, and complexity. The BDS test determined nonlinearity, and later, the time-dependent correlation matrix was obtained by using the stochastic SO(2) Lie group. Finally, we obtained robustness check results. Our results showed that the time-dependent correlation matrix obtained by using the stochastic SO(2) Lie group method yielded more successful results than the ordinary correlation and covariance matrix and the Spearman correlation and covariance matrix. If policymakers, financial managers, risk managers, etc., use the standard correlation method for economy or financial policies, risk management, and financial decisions, the effects of nonlinearity, fractionality, entropy, and chaotic structures may not be fully evaluated or measured. In such cases, this can lead to erroneous investment decisions, bad portfolio decisions, and wrong policy recommendations. Full article

In this article, we introduce a novel deep learning hybrid model that integrates attention Transformer and gated recurrent unit (GRU) architectures to improve the accuracy of cryptocurrency price predictions. By combining the Transformer’s strength in capturing long-range patterns with GRU’s ability to model short-term and sequential trends, the hybrid model provides a well-rounded approach to time series forecasting. We apply the model to predict the daily closing prices of Bitcoin and Ethereum based on historical data that include past prices, trading volumes, and the Fear and Greed Index. We evaluate the performance of our proposed model by comparing it with four other machine learning models, two are non-sequential feedforward models: radial basis function network (RBFN) and general regression neural network (GRNN), and two are bidirectional sequential memory-based models: bidirectional long short-term memory (BiLSTM) and bidirectional gated recurrent unit (BiGRU). The model’s performance is assessed using several metrics, including mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE), along with statistical validation through the non-parametric Friedman test followed by a post hoc Wilcoxon signed-rank test. Results demonstrate that our hybrid model consistently achieves superior accuracy, highlighting its effectiveness for financial prediction tasks. These findings provide valuable insights for enhancing real-time decision making in cryptocurrency markets and support the growing use of hybrid deep learning models in financial analytics. Full article

This study examines the impact of the coronavirus disease 2019 (COVID-19) pandemic on market efficiency by analyzing three time series—price returns, absolute returns, and volatility increments—in the stock (Deutscher Aktienindex, Nikkei 225, Shanghai Stock Exchange (SSE), and Volatility Index) and cryptocurrency (Bitcoin and Ethereum) markets. The effect is found to vary by asset class and market. In the stock market, while the pandemic did not influence the Hurst exponent of volatility increments, it affected that of returns and absolute returns (except in the SSE, where returns remained unaffected). In the cryptocurrency market, the pandemic did not alter the Hurst exponent for any time series but influenced the strength of multifractality in returns and absolute returns. Some Hurst exponent time series exhibited a gradual decline over time, complicating the assessment of pandemic-related effects. Consequently, segmented analyses by pandemic period may erroneously suggest an impact, warranting caution in period-based studies. Full article

The cryptocurrency market presents immense opportunities and significant risks due to its high volatility. Accurate price forecasting is crucial for informed investment decisions, enabling investors to optimize portfolio allocation, mitigate risk, and potentially maximize returns. Existing forecasting methods often struggle with the inherent non-stationarity and complexity of cryptocurrency price dynamics. This study addresses this challenge by developing a system for high-frequency forecasting of the closing prices of ten leading cryptocurrencies. We compare various machine learning models, including recurrent neural networks (RNNs), time series analysis (ARIMA), and conventional regression algorithms, using minute-step Bitcoin price data over a 30-day period to predict prices 60 min ahead. Our findings demonstrate that the GRU neural network exhibits superior predictive accuracy (MAPE = 0.09%, MSE = 5954.89, RMSE = 77.17, MAE = 60.20), outperforming other models considered. This improved forecasting accuracy contributes to the existing literature by providing empirical evidence for GRU’s effectiveness in the volatile cryptocurrency market and offers practical insights for investment strategies. A web application integrating the best-performing model further facilitates real-time price prediction for multiple cryptocurrencies. Full article

As crypto assets become more widely adopted, crypto asset markets and traditional financial markets may become increasingly interconnected. The close linkages between these markets have potentially important implications for price formation, contagion, risk management and regulatory frameworks. In this study, we assess the correlation between traditional financial markets and selected crypto assets, study factors that may impact the price of crypto assets and identify potentially significant events that may have an impact on Bitcoin and Ethereum price dynamics. For the latter analyses, we adopt a Bayesian model averaging approach to identify change points in the Bitcoin and Ethereum daily price time series. We then use the dates and probabilities of these change points to link them to specific events, finding that nearly all of the change points can be associated with known historical crypto asset-related events. The events can be classified into broader geopolitical developments, regulatory announcements and idiosyncratic events specific to either Bitcoin or Ethereum. Full article