This paper investigates the volatility dynamics and underlying long memory features of four major cryptocurrencies-Bitcoin, Ethereum, Litecoin, and Ripple-which were selected due to their high liquidity, large trading volumes, and historical significance in the digital asset market. The long-range dependence exhibited in cryptocurrency markets is often overlooked. However, based on the strong evidence of persistent dependence in the return series, we adopt advanced volatility models that are capable of accommodating high volatility and heavy-tails, as well as the long memory properties of cryptocurrencies. Specifically, we employ long-memory extensions of the GAS (Long memory GAS) and GARCH (Fractionally Integrated Asymmetric Power ARCH) models, integrating heavy-tailed innovation distributions: the Generalized Hyperbolic Distribution (GHD) and Generalized Lambda Distribution (GLD). Standard GARCH and GAS models are included as benchmarks. The performance of the models are assessed using Value-at-Risk (VaR) estimation, backtesting (in-sample and out-of-sample) and volatility forecasting metrics. The results indicate that long memory models, particularly the FIAPARCH model, consistently outperforms the standard GAS and GARCH models in capturing tail risk and the volatility persistence. These findings emphasize the critical role of long memory in modeling the risk of cryptocurrencies, indicating that accounting for volatility persistence can significantly enhance the accuracy of risk estimates and strengthen risk management practices.
Chapter 1 of âCryptocurrency Market Forecasting with Catboost Modelsâ explores the role of FinTech in transforming the financial sector through advanced technologies like blockchain, AI, and IoT. It discusses how these technologies enhance efficiency, accessibility, and economic growth, focusing mainly on their application in financial services and market forecasting.
Whether financial assets movements exhibit correlation and memory has been an intriguing question for physicists. This study aims to investigate whether financial shocks exhibit non-Markovian behavior. In particular, it explores the presence of long-term memory and non-local fluctuations during financial crises. The non-Markovian behavior of volatility and return during the cryptocurrency crashes of 2017â2021 and 2021â2024 cycles are examined. The analysis shows that a scaling relation, which is valid for a singular Markovian process, breaks down in data sets spanning approximately 1 year and 3 years after the onset of the 2017 crash. A similar pattern was observed in the 2021 crash, although the analysis does not work for some data sets. In these time intervals, the crash process shows non-Markovian behavior with financial shocks demonstrating non-local fluctuations and evidence of long-term memory.
Phumudzo Lloyd Seabe, Claude Rodrigue Bambe Moutsinga, Edson Pindza
Abstract Predicting cryptocurrency prices is challenging due to market volatility and external influences like social media sentiment. This study integrates Twitter sentiment analysis with deep learning models (LSTM, GRU, Bi-LSTM, and Temporal Attention Model) to enhance Bitcoin price forecasting. Sentiment features were extracted using VADER and RoBERTa, with findings showing that RoBERTa-based models significantly outperform VADER. Bi-LSTM (RoBERTa) achieved the lowest MAPE of 2.01%, demonstrating the effectiveness of deep contextual embeddings. SHAP analysis identified Sentiment Momentum, RoBERTa Compound Score, and VADER Negativity Score as key predictors of price movements. These results highlight the value of sentiment-driven forecasting and provide insights for traders, investors, and researchers.
We analyze Trumpâs memecoin launch, showing heterogeneous volatility spillovers driven by sentiment and fundamentals. Political signals amplified speculative dynamics, underscoring how politics increasingly shapes cryptocurrency markets and investor behavior.
David Umoru, Malachy Ashywel Ugbaka, Anake Fidelis Atseye, Samuel Manyo Takon ¡ 18 authors
The financial market is a decentralized market made up of global network of businesses, forex, stock investment, and digital markets. The paper evaluated the patterns and interrelationships of volatilities in return amongst foreign exchange, stock, and bitcoin markets returns in oil importing nations. The Markov-Switching and quantile regression estimation methods were executed. Results indicate stock markets of Kenya and Uganda had the most frequent depreciating returns. Bitcoin returns were negatively and significantly influenced by changes in currency values, whereas change in bitcoin trading value causes a higher change in exchange rate returns. A percentage increase in stock market returns stimulates exchange rate returns to rise also but at a higher rate. Returns on exchange rates and Bitcoin markets are significant predictors of stock market returns. Exchange rate volatility dynamics occur in the opposite direction as those in stock markets and in the floor of Bitcoin market. Volatility was significantly observed when currency devalued confirming the erratic behaviors of investors to dwindling local currency values compared to the U.S. dollar. Financial markets authorities can use the research findings to support their choice to regulate the financial markets and shield investors from information asymmetry that could result from cross-market volatility interrelationships.
This paper investigates Bitcoinâs resilience against the U.S. dollarâwidely recognized as the global reserve currencyâby 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 measuresâparticularly the Frobenius norm of wavelet coherence and an exponential decay phase-weighting schemeâreveal that Bitcoinâs 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 euroâs dominant influence in the DXY, BTC continues to show weaker coupling than mainstream assetsâreinforcing 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 worldâs leading reserve currencyâthe U.S. dollarâhas significant implications for both investors and policymakers.
Cryptocurrencies have emerged as a cornerstone of the digital transformation in the global economy during the last decades, introducing decentralized mechanisms that challenge the dominance of traditional financial systems. This innovation enhances transparency, security, and accessibility, while making financial systems more inclusive and efficient. Since the first inception of Bitcoin in 2009, the cryptocurrency landscape has expanded exponentially. By 2023, the combined market capitalization of over 22,000 cryptocurrencies exceeded $1 trillion, demonstrating their significant influence on financial markets. This study examines the dual nature of cryptocurrenciesâassessing their transformative potential and inherent risks. Using case studies, historical data, and technological advancements, it provides a balanced perspective on how cryptocurrencies can reshape financial systems, bridge economic inclusion gaps, and drive innovation.
PURPOSE: This study aims to investigate psychological and behavioral mechanisms and their impact on the cryptocurrency market. The analysis is carried out through the prism of studying the FOMO phenomenon.
Abstract We use transaction-level data from the Bitcoin exchange Mt.Gox, including over 1.4 million transactions from more than 45,000 traders, to investigate the role of technical chart patterns in the early Bitcoin market from April 2011 to September 2013. Employing a pattern recognition algorithm, we identify hourly trading signals for five major chart patterns. Buy signals of these patterns are associated with an average increase in abnormal trading volume of more than 53%. Trades executed during buy signal periods yield significantly higher average returns than those made during non-signal periods. Traders who use chart patterns more frequently are more likely to generate right-skewed return distributions, engage in more active trading, and achieve higher average roundtrip returns. Our research suggests that chart pattern trading was a crucial tool for Mt.Gox clients, highlighting the importance of technical heuristics in shaping the dynamics in a less efficient and unregulated market environment. By leveraging a comprehensive transaction dataset from a major cryptocurrency exchange, we provide unique insights into the actual trading behavior of the first Bitcoin adopters. This sets our work apart from previous studies that mainly rely on backtesting technical strategies using publicly available price data.
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 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 periods may erroneously suggest an impact, warranting caution in period-based studies.
Chiara Oldani, Giovanni S. F. Bruno, Marcello Signorelli
This paper investigates the existence of bubbles in the daily prices of the most popular cryptocurrencies, Bitcoin (BTC), Ether (ETH), and Ripple (XRP), employing the recursive methods of Phillips et al. (2015) and Phillips et al. (2011) for testing and date-stamping episodes of exuberant behaviour over a period spanning seven years (2018â2024), including the COVID-19 pandemic crisis (2020â2021). The critical values of the tests are computed through the composite wild bootstrap technique by Phillips and Shi (2020) to make them robust to time-varying unconditional heteroscedasticity and the multiplicity issue in recursive tests. Results indicate that the prices of the most popular cryptocurrencies traded on decentralized ledgers, BTC and ETH, exhibited multiple episodes of exuberant behaviour, unambiguously for BTC and depending on the tests for ETH. Bubbles detected in the prices of BTC were due to the halving of the crypto, to market exuberance and to the pandemic crisis; bubbles detected on ETH prices were due to the launch of NFTs on the Ethereum blockchain, and to the change in investorsâ expectations (from exuberant to pessimistic); the change in the stance of monetary policy burst the bubbles of BTC and ETH prices in 2024. No test supports the exuberance of XRP that is traded on a centralized ledger; weekly data confirm the absence of multiple bubbles. By looking at the presence of bubbles in these different digital ecosystems, we also consider how the technological differences can impact, possibly asymmetrically, bubbles' formation.
We text-mine 2,125,788 posts on Bitcointalk.org from January 2014 to June 2024 to explore the link from differences of emotion among investors to Bitcoinâs extraordinary prices swings. The cross-sectional width of emotions, i.e. emotional difference, is statistically significantly associated with Bitcoinâs volatility. The least absolute shrinkage and selection operator (LASSO) method and the nonlinear iterative partial least squares (NIPALS) â variable importance-in-projection (VIP) algorithm also ascertain that Bitcoin prices may mainly reflect the view of highly emotional investors, making Bitcoinâs volatility more aligned with the cross-section of emotions. We do not argue that the profession needs to abandon the laissez-faire approach to cryptocurrencies. Rather, we call for investor education to mitigate individual-level psychological biases and emotional actions.
Muhammad Muzammil, Abisheka Pitumpe, Xigao Li, Amir Rahmati ¡ 5 authors
Governments and regulatory bodies have recognized investment scams as a prevalent form of cryptocurrency fraud. These scams typically use professional-looking websites to lure unsuspecting victims with promises of unrealistically high returns. In this paper, we introduce Crimson, a distributed system designed to continuously detect cryptocurrency investment scam websites as they are created in the wild. During the first 8 months of 2024, Crimson processed approximately 6 billion domain names and classified 43,572 unique cryptocurrency investment scam websites in real-time. Beyond detection, we provide insights into the design and infrastructure of these websites that can help users recognize scam patterns and assist hosting providers in detecting and blocking such sites. Furthermore, we investigate the inclusion of our detected scam websites in block-lists used by popular web browsers and applications, finding that the vast majority of these websites were absent. On the financial side, by analyzing the transactions incoming to scammer wallets on 6.7% of the sites detected by Crimson, we observe an estimated lower bound of 2.04M USD in losses due to cryptocurrency investment scams.
This paper investigates the temporal evolution of cryptocurrency time series using information measures such as complexity, entropy, and Fisher information. The main objective is to differentiate between various levels of randomness and chaos. The methodology was applied to 176 daily closing price time series of different cryptocurrencies, from October 2015 to October 2024, with more than 30 days of data and not completely null. Complexityâentropy causality plane (CECP) analysis reveals that daily cryptocurrency series with lengths of two years or less exhibit chaotic behavior, while those longer than two years display stochastic behavior. Most longer series resemble colored noise, with the parameter k varying between 0 and 2. Additionally, Natural Language Processing (NLP) analysis identified the most relevant terms in each white paper, facilitating a clustering method that resulted in four distinct clusters. However, no significant characteristics were found across these clusters in terms of the dynamics of the time series. This finding challenges the assumption that project narratives dictate market behavior. For this reason, investment recommendations should prioritize real-time informational metrics over whitepaper content.
This paper explores temporal coordination mechanisms in market economies through the lens of Austrian Capital Theory, emphasizing how interest rates facilitate the alignment of complex intertemporal production plans across dispersed market participants. The study addresses the challenge of coordinating heterogeneous capital goods over time, a critical issue in dynamic economic systems where production spans multiple stages and horizons. Through a rigorous theoretical analysis and an extensive literature review, the research investigates the role of market processes in achieving this coordination, with a particular focus on how monetary policy influences these mechanisms. The analysis reveals that interest rates act as vital signals, aggregating dispersed knowledge and guiding entrepreneurial decisions to align production structures with consumersâ time-preferences. However, monetary interventions, such as interest rate manipulations, are shown to distort these signals systematically, contributing to malinvestmentâwhere resources are misallocated to unsustainable projectsâand overconsumption during business cycles. Empirical evidence from the 2002â2009 period, including the U.S. Federal Reserveâs monetary expansion, illustrates these effects, highlighting how negative real interest rates (2003â2005) falsified economic calculations, inflating household net worth by $21.7 trillion while reducing savings rates to below 1% by 2005, only to collapse by $13 trillion in 2008. This research synthesizes Austrian insights with emerging technological developments, particularly Web 3.0 technologies and decentralized systems like smart contracts and decentralized finance (DeFi), which may enhance market coordination by reducing reliance on central intermediaries and improving knowledge transmission. The originality lies in bridging classical economic theory with modern technological paradigms, offering a framework to assess how decentralized innovations can preserve Austrian principles of entrepreneurial discovery and spontaneous order. This theoretical analysis contributes to understanding the interplay between monetary policy, technology, and market dynamics, providing a foundation for future empirical studies on decentralized economic coordination.
Mohammad Inairat, Nema Abuhelou, Mohammed A. Afifi, Nizar Sahawneh ¡ 6 authors
The rapid transformation of technology in financial services has greatly highlighted the need for precise and secure financial forecasting models. Nevertheless, the centralized analysis of financial data is being increasingly limited by privacy legislation and the possibility of data infringement. Federated Learning (FL) appears as a groundbreaking concept, allowing for decentralized model training over various data sources without losing the privacy of the data. The paper investigates the implementation of FL in the decentralized financial forecasting while addressing important issues such as data diversity, communication overload, and non-IID financial dataset model optimization. Using the real-world datasets we assess the efficiency of FL frameworks against the existing centralized methods, thus exposing the higher precision, safety, and ability to scale in forecast viability. The results show the promise of FL in changing the process of financial forecasting, issuing solid estimates of future events while protecting sensitive financial information. This study could be seen as an initial step towards a more widespread application of FL in finance which could lead to the promotion of innovations in secure and decentralized analysis of data.
Traditional portfolio optimization techniques predominantly rely on the classical meanâvariance framework introduced by Markowitz, which focuses on balancing expected returns against risk, typically measured by variance. However, in volatile and structur-ally unstable markets such as cryptocurrencies, this approach often fails to capture the full spectrum of uncertainty and diversification potential. This paper introduces an al-ternative methodology grounded in entropy, a fundamental concept in information theory that quantifies uncertainty and disorder. By incorporating entropy into the portfolio optimization process, we offer a more generalizable, distribution-free approach that enhances diversification and resilience.We develop and analyze three distinct en-tropy-based models: the maximum Shannon entropy model, the second-order entropy (Tsallis) model, and the maximum weighted Shannon entropy model. These formula-tions extend the traditional meanâvariance approach by integrating nonlinear uncer-tainty measures, enabling a richer representation of investor preferences and asset in-terdependencies. Analytical solutions to the proposed models are derived using the method of Lagrange multipliers, ensuring mathematical rigor and interpretability.The proposed models are empirically validated using a portfolio composed of four leading cryptocurrenciesâBitcoin (BTC), Ethereum (ETH), Solana (SOL), and Binance Coin (BNB)âwith market data from January to March 2025. The case studies demonstrate how entropy-based optimization leads to well-diversified portfolios, robust under market turbulence and heavy-tailed return distributions. Notably, the models facilitate dynamic adjustments in asset allocation in response to shifts in returnârisk characteristics and entropy levels. This study contributes to the ongoing generalization of portfolio theory by positioning entropy as both a diversification enhancer and a structural risk measure. It provides theoretical insight, practical tools for asset allocation in high-volatility environments, and paves the way for future research in entropy-driven financial optimization frameworks.