Accurate and efficient cryptocurrency price prediction is vital for investors in the volatile crypto market. This study comprehensively evaluates nine modelsâincluding baseline, zero-shot, and deep learning architecturesâon 21 major cryptocurrencies using daily and hourly data. Our multi-dimensional evaluation assesses models based on prediction accuracy (MAE, RMSE, MAPE), speed, statistical significance (DieboldâMariano test), and economic value (Sharpe Ratio). Our research found that the optimally fine-tuned TimeGPT model (without variables) demonstrated superior performance across both Daily and Hourly datasets, with its statistical leadership confirmed by the DieboldâMariano test. Fine-tuned Chronos excelled in daily predictions, while TFT was a close second to TimeGPT for hourly forecasts. Crucially, zero-shot models like TimeGPT and Chronos were tens of times faster than traditional deep learning models, offering high accuracy with superior computational efficiency. A key finding from our economic analysis is that a modelâs effectiveness is highly dependent on market characteristics. For instance, TimeGPT with variables showed exceptional profitability in the volatile ETH market, whereas the zero-shot Chronos model was the top performer for the cyclical BTC market. This also highlights that variables have asset-specific effects with TimeGPT: improving predictions for ICP, LTC, OP, and DOT, but hindering UNI, ATOM, BCH, and ARB. Recognizing that prior research has overemphasized prediction accuracy, this study provides a more holistic and practical standard for model evaluation by integrating speed, statistical significance, and economic value. Our findings collectively underscore TimeGPTâs immense potential as a leading solution for cryptocurrency forecasting, offering a top-tier balance of accuracy and efficiency. This multi-dimensional approach provides critical, theoretical, and practical guidance for investment decisions and risk management, proving especially valuable in real-time trading scenarios.
This paper investigates the dependence structure between returns and trading volumes for five major cryptocurrencies: Bitcoin, Cardano, Ethereum, Litecoin, and Ripple. Using a copula-based framework, we focus on a mixture of the Joe copula and its 90-degree rotation to capture asymmetric relationships, especially in the tails of the distribution. Our findings reveal significant upper and lowerâupper tail dependencies, suggesting that extreme trading volumes are associated with both positive and negative return extremes. The results confirm a nonlinear and asymmetric volumeâreturn relationship, which traditional linear models fail to capture.
Traditional portfolio optimization models, rooted in the meanâvariance framework of Markowitz, rely heavily on variance as a risk measure. Although theoretically elegant, this approach becomes fragile in volatile and structurally unstable markets such as cryptocurrencies, where return distributions deviate significantly from normality, cor-relations are unstable, and concentration risk emerges. These limitations have motivated the search for alternative frameworks capable of capturing uncertainty in a more flexible and distribution-free manner. Entropy, originally introduced by Shannon as a measure of information, has gradually been recognized in the financial literature as a suitable proxy for diversification and systemic uncertainty. To address the shortcomings of variance-based models, this paper introduces the Weighted Shannon Entropy (WSE) model as a diversification-oriented alternative. By extending the classical Shannon entropy with asset-specific informational weights, the WSE framework provides additional flexibility for modeling heterogeneous asset char-acteristics, such as liquidity, informational value, or perceived reliability. Using the principle of maximum entropy and the method of Lagrange multipliers, we derive ex-ponential-form solutions for portfolio weights that naturally discourage concentration, ensure balanced allocations, and remain analytically tractable. The methodology is validated empirically on a portfolio of four leading cryptocurren-ciesâBitcoin (BTC), Ethereum (ETH), Solana (SOL), and Binance Coin (BNB)âusing market data from January to March 2025. The results demonstrate that the entropy-based optimization framework produces well-diversified portfolios, robust to volatility and structural instability, and provides a distribution-free alternative to the classical meanâvariance model. Beyond its empirical performance, the WSE formulation highlights the conceptual advantage of entropy in integrating return, risk, and diversification into a single unified framework. The paper contributes both theoretically and practically: it strengthens the mathematical foundation of entropy-based portfolio selection, extends its applicability to digital asset markets, and illustrates how weighting schemes can enrich the classical Shannon measure. Future research may extend this approach to multi-period optimization, gen-eralized entropies such as Tsallis and Kaniadakis, or integration with machine learning models for dynamic portfolio management.
Ronald Ravinesh Kumar, Hossein Ghanbari, Peter Josef Stauvermann
The market for digital assets, and more specifically cryptocurrencies, is growing, although their adoption in small island countries remains absent. This paper explores the potential benefits of integrating cryptocurrencies into portfolios alongside stocks, with a focus on Fijiâs stock market. This is the first study on a small market like Fiji, which emphasizes the role of cryptocurrencies in portfolio management. We analyze the outcomes (returns and risks) of combining cryptocurrencies with stocks using 12 different techniques. We use monthly stock returns data of 18 companies listed on the South Pacific Stock Exchange from Aug-2019 to Jun-2025 (71 months) and nine cryptocurrencies from Sept-2019 to Jun-2025 (70 months). Our main analysis shows that only one cryptocurrency, albeit with a small exposure, consistently appears in the stock-cryptocurrency portfolios in the 12 methods. Using the return-to-risk ratio across methods as a guide, we find that the stocks-cryptocurrencies portfolio based on EQW, MinVar, MaxSharpe, MinSemVar, MaxDiv, MaxDeCorr, MaxRMD, and MaxASR offers better outcomes than the stock-only portfolios. Using high returns as a guide, we find that six out of 12 methods (EQW, MaxSharpe, MaxSort, MaxCEQ, MaxOmega, and MaxUDVol) support the stocks-cryptocurrencies portfolios. Portfolios satisfying both conditions (high return-risk ratio and high return) are supported by the EQW and MaxSharpe portfolios. The consistency of assets in both stock and stockâcryptocurrency portfolios is further confirmed by 24-month out-of-sample forecasts and Monte Carlo simulations, although the latter supports small exposures in two out of the nine cryptocurrencies. Based on the results, we conclude that a small exposure to certain cryptocurrencies can strengthen diversification and improve potential returns.
Accreditation has historically played a central role in securities regulation, seeking to balance investor protection, market access, and capital formation. Traditionally, regulatory frameworks have relied on wealth or income thresholds as proxies for investor sophistication, premised on the assumption that individuals with greater financial resources are better equipped to manage risk and obtain professional advice. However, in rapidly evolving crypto-asset markets, these wealth-based criteria have become increasingly misaligned with market realities. Such thresholds frequently exclude technically proficient but less affluent participants, thereby perpetuating inequality and conflicting with the inclusive ethos of digital finance. Moreover, these criteria have failed to prevent significant losses among wealthy accredited investors, as evidenced by the collapses of Terra-Luna, Three Arrows Capital, and FTX. Competence-based frameworks are still underdeveloped, unevenly applied, and can become overly formal, while traditional disclosure rules do not fully address the technical and behavioral challenges of decentralized finance. This article takes a critical look at accreditation in crypto-asset markets, drawing on legal, empirical, and normative analysis. By comparing the United States, European Union, Singapore, and Russia, and examining cases like the ICO boom, Singaporeâs regulatory sandboxes, and the Terra-Luna and FTX collapses, the article shows that wealth-based accreditation falls short in fairness and effectiveness. It proposes a hybrid approach that combines competence assessments, crypto-specific disclosure, prudential safeguards, regulatory sandboxes, and international cooperation. This article contends that reforming accreditation constitutes a fundamental transformation in the approach to investor protection, advancing principles of fairness, legitimacy, and systemic robustness. By introducing a hybrid framework grounded in fairness and empirical evidence, the article contributes to policy discourse and informs scholarly understanding of the evolution of financial regulation in the context of digital innovation.
This paper proposes a cryptocurrency portfolio trading system (CPTS) that optimizes trading performance in the cryptocurrency futures market by leveraging reinforcement learning and timeframe analysis. By employing the advantage actorâcritic (A2C) algorithm and analysis of variance (ANOVA) portfolios are constructed over multiple timeframes. Data corresponding to the trade of 18 major cryptocurrencies on Binance Futuresââbetween January 2022 and December 2023ââare used to show that trading strategies can be effectively categorized into those with high-frequency (10, 30, and 60 min) and low-frequency (daily) timeframes. Empirical results demonstrate statistically significant differences in returns between these timeframe groups, with major cryptocurrencies (e.g., Bitcoin and Ethereum) exhibiting higher returns in high-frequency trading (16â17%) than in daily trading (6â7%) during training. Performance evaluation during the test period revealed that the low-frequency group achieved a 43.06% average return, significantly outperforming the high-frequency group (5.68%). The ANOVA results confirm that both the frequency type and portfolio selection significantly influence trading performance at the 5% significance level. This study offers a novel approach to cryptocurrency trading that considers the distinct characteristics of different timeframes. The effectiveness of combining reinforcement learning with statistical analysis for portfolio optimization in highly volatile cryptocurrency markets is demonstrated.
Cryptocurrency markets are highly volatile and influenced by both price trends and market sentiment, making effective portfolio management challenging. This paper proposes a dynamic cryptocurrency portfolio strategy that integrates technical indicators and sentiment analysis to enhance investment decision-making. Market momentum is captured using the 14-day Relative Strength Index (RSI) and Simple Moving Average (SMA), while sentiment signals are extracted from news articles with VADER and further validated using the Google Gemini large language model. These signals are incorporated into expected return estimates and used in a constrained mean-variance optimization framework. Backtesting across multiple cryptocurrencies shows that the integrated approach outperforms traditional benchmarks, including momentum strategy, Bitcoin Long-Short strategy, and an equal-weighted portfolio, achieving stronger risk-adjusted returns and more consistent cumulative growth. Furthermore, comparing the sentiment-only and technical-only strategies shows that incorporating sentiment information alongside technical indicators can lead to more consistent performance gains. However, the strategies exhibit substantial drawdowns that coincide with known periods of market stress, indicating that additional risk-management components are required to improve stability.
Independent Algorithmic Trading Consultant and Quantitative Researcher serving international financial institutions Los Angeles, USA, Maksim Baradziuk
The study is devoted to identifying and analyzing the synergistic interaction between the theoretical principles of behavioral finance and applied methodologies for developing high-r eturn algorithmic strategies in the digital asset segment. In conditions where the efficient market hypothesis demonstrates limitations in its applicability, especially in environments with increased volatility and underdeveloped infrastructureâsuch as cryptocurrency markets and decentralized finance (DeFi) ecosystemsâbehavioral biases emerge as important determinants of market inefficiency. The paper presents a framework that combines the targeted exploitation of cognitive patterns, including the disposition effect and the phenomenon of herd behavior, with the application of advanced technological solutions. Based on four original case studiesâranging from the development of a proprietary backtesting mechanism incorporating elements of chaotic process modeling to the construction of a predictive risk management system for DeFiâthe practical implementation of the proposed approach is demonstrated. The results obtained confirm the superiority of the hybrid architecture over traditional methods: from effectively reducing crash risk in DeFi carry trade strategies to maintaining portfolio resilience under market stress conditions and generating ultra-high returns (CAGR exceeding 200% with MDD of 30%). The studyâs findings reinforce the validity of the adaptive markets hypothesis and confirm the applied value of the synthetic methodology for modern algorithmic trading. The information reflected in the study will be of interest to asset managers, quantitative fund specialists, and researchers focused on creating next-generation algorithms.
Among the plethora of literature on interlinkages in markets, more focus has been on peripheral factors. This study attempts to fill this gap by exploring volatility as driver for interlinkages between Bitcoin, Ethereum, Tether, USD-Coin, Binance Coin (BNB), and the crypto-volatility-index (CVI) from April 2019 to August 2022. Using various wavelet techniques, the study depicts significant interlinkages across short-term, medium-term, and long-term horizons, with relatively stronger interlinkages in the long term. The findings confirm that while CVI does not drive these interlinkages, Ethereum, Bitcoin, and CVI play dominant roles in the short, interim, and medium-term periods, respectively, offering new insights into the dynamism of cryptocurrency markets.
In recent years, computational intelligence techniques have significantly contributed to the automation and optimization of trading strategies. Despite the increasing sophistication of predictive models, classical technical indicators such as dual Simple Moving Averages (2-SMA) remain popular due to their simplicity and interpretability. This work proposes an adaptive trading system that combines the 2-SMA strategy with a learning-based metaheuristic optimizer known as the Learning-Based Linear Balancer (LB2). The objective is to dynamically adjust the strategyâs parameters to maximize returns in the highly volatile cryptocurrency market. The proposed system is evaluated through simulations using historical data of the BTCUSDT futures contract from the Binance platform, incorporating real-world trading constraints such as transaction fees. The optimization process is validated over 34 training/test splits using overlapping 60-day windows. Results show that the LB2-optimized strategy achieves an average return on investment (ROI) of 7.9% in unseen test periods, with a maximum ROI of 17.2% in the best case. Statistical analysis using the Wilcoxon Signed-Rank Test confirms that our approach significantly outperforms classical benchmarks, including Buy and Hold, Random Walk, and non-optimized 2-SMA. This study demonstrates that hybrid strategies combining classical indicators with adaptive optimization can achieve robust and consistent returns, making them a viable alternative to more complex predictive models in crypto-based financial environments.
This study employs novel quantile time-frequency connectedness approach to explore the dynamic connectedness among sustainable assets (sustainable, green bond, and clean energy index), traditional assets (traditional index and crude oil), and cryptocurrency. This method assesses the impact of uncertain events on asset relationships. Findings indicate median connectedness of 36.94% in the short run and 4.81% in the long run, with short-term dynamics dominating system transmission. The traditional index is the primary transmitter of short-run shocks, while the green bond index leads in long-run shocks. Diversification across asset classes is recommended for effective hedging and optimal returns during extreme market conditions.
This paper provides a systematic review and synthesis of two converging financial literatures: mortgage-backed securities (MBS) and decentralized finance (DeFi). I trace the evolution of MBS research from the 1970s through the 2008 financial crisis to present day, while examining how blockchain innovations create new possibilities for real estate finance. The methodology combines traditional literature review techniques with bibliometric analysis, utilizing Google Scholar and Google Trends data to document the shifting research landscape and public interest in these topics over time. The findings reveal that while MBS research peaked following the 2008 financial crisis, DeFi and real estate tokenization research show more recent growth trajectories since 2016. The synthesis highlights how blockchain technology offers potential improvements in transparency, transaction costs, and liquidity for real estate markets, while acknowledging significant regulatory and governance challenges. This review contributes to understanding the current state of research at the intersection of traditional real estate finance and emerging blockchain applications, providing a foundation for future empirical investigations.
ABSTRACT This study investigates how overconfident cryptocurrency traders influence the connection between returns and risk premia, proxied by optionâadjusted credit spreads. Using daily data from January 2021 to February 2025, we uncover asymmetry and state dependence: returns decline when spreads widen, particularly during crashes, yet they do not recover when spreads narrow. Equity indices exhibit more balanced coâmovements. The asymmetry strengthens in highâvolatility periods and persists after we control for broad market returns and after we substitute a composite crypto index for individual cryptocurrencies. These findings indicate a distinctive pricing mechanism in cryptocurrency markets shaped by overconfident behaviour and creditâspread dynamics.
Erdinç Akyıldırım, Ahmet Faruk Aysan, OÄuzhan Ăepni, Shaen Corbet
This study investigates the influence of news-based sentiment on the returns of Decentralized Finance (DeFi) coins using a sample of 27 coins from January 2017 to March 2022. Our results indicate that news sentiment significantly impacts DeFi returns, with negative sentiment exerting a stronger influence than positive sentiment. Transaction volume and network security also emerge as critical drivers of DeFi coin returns. Smaller coins are more sensitive to news sentiment, showing greater return volatility. The impact of news-based sentiment is more pronounced during weekdays, likely due to reduced participation by institutional investors and trading algorithms. These findings have important implications for investors and policymakers, suggesting multiple pathways for market manipulation under specific conditions. âą We investigate the relationship between DeFi coins and news-based sentiment. âą Negative sentiment has a greater impact on returns. âą Transaction volume and network security drive returns. âą Smaller DeFi coins are more susceptible to news sentiment and greater return volatility. âą DeFi returnsâ sensitivity to news-media sentiment is significantly elevated during weekdays.
We investigate the high-frequency dynamics of Bitcoin and Ethereum perpetual futures traded on Binance from January 2020 to December 2024. After a thorough discussion of the stylized facts and particularities of Bitcoin perpetual futures, based on previous research in futures markets, we evaluate the fit of two competing models of market microstructure: the Mixture of Distributions Hypothesis (MDH) and the Intraday Trading Invariance Hypothesis (ITIH). Using intraday data at different levels of aggregation, we investigate the relationship between return volatility per transaction and trade size. We find evidence favoring the MDH in the crypto futures market.
This study constructs a machine learning-driven multi-factor model for Ethereum quantitative trading, combining traditional technical indicators (RSI, MACD), on-chain metrics (gas usage, active addresses), and X platform social sentiment to predict short-term returns. Backtesting from Q4 2021 to Q3 2024, using online learning and genetic algorithms for dynamic factor updates, yields a 97% annualized return, a Sharpe ratio of 2.5, and an information ratio of 1.2, outperforming Ethereum's raw returns. Simulated trading in Q4 2024 (bull market) achieves a 33% quarterly return with an 18% maximum drawdown, while Q1 2025 (bear market) records a -10% quarterly return with a 12% drawdown, confirming robustness. Technical and sentiment factors drive performance, though a 22% maximum drawdown in backtesting highlights volatility risks. An optimal Z-score threshold (±1.0) and 4-hour trading frequency balance profitability and costs. Future enhancements include high-frequency mainnet data integration and advanced risk management to strengthen model resilience in Ethereum's volatile market.
Margherita Renieri, Letterio Galletta, Alberto Lluch Lafuente, Aleksander Junge · 5 authors
Automated Market Makers ( AMM s) are one of the most used Decentralized Finance services enabling users to exchange crypto-assets directly without intermediaries. However, current protocols impose significant constraints on the liquidity levels required for transactions. In this paper, we propose a liquidity-saving mechanism designed to minimize the liquidity required by AMM services. Our mechanism delays the transactions violating the liquidity constraints in a queue, and, when certain conditions are met, it selects from the queue a feasible transaction sequence that fulfills the constraints and executes them atomically on the blockchain. We provide an operational semantics of such a mechanism that precisely characterizes the interactions between users and AMM s and the conditions when the liquidity-saving mechanism is triggered. Moreover, we show that our mechanism allows for novel liquidity saving behavior for multi-party exchange, multi- AMM arbitrage, and enhances user intent compared to traditional AMM s. Finally, to validate our approach, we develop a simulator and experiment with various application scenarios, yielding insights into the practical implications of our mechanism.
Xinran Huang, Linzhi Tan, Haozhe Su, Jeremy EngâTuck Cheah
ABSTRACT One of the critical risks associated with cryptocurrency assets is the soâcalled downside risk, or tail risk. Conditional ValueâatâRisk (CVaR) is a measure of tail risks that is not normally considered in the construction of a cryptocurrency portfolio. In this paper, we propose a new approach to portfolio construction based on a deep learning CVaR utility function. This approach is designed to address the issue of tail risk. We evaluate the performance of this approach in comparison to other portfolio construction techniques, including the naĂŻve, minimum variance and meanâvariance portfolios. Our findings indicate that the proposed approach outperforms traditional optimisation models.
Abstract This research examines the dynamics of the non-fungible tokens (NFT) market by utilizing key financial metrics such as Bitcoin prices, the Crypto Fear-Greed Index, and DeFi indicators. It analyzes NFT-USD values, the Crypto Fear-Greed Index, total value locked in DeFi, and Bitcoin interactions between February 2021âJuly 2023. Employing ordinary least squares regression, quantile regression, Johansen cointegration, and VECM Granger analysis, the study uncovers complex relationships shaping the NFT market. The findings reveal a positive correlation between Bitcoin prices and NFT values, a negative relationship between total value locked in DeFi and NFT values, and an inverse connection between the Crypto Fear-Greed Index and NFT values. Additionally, cointegration exists among the variables, and causality analysis indicates that Bitcoin influences total value locked, while shifts in the Crypto Fear-Greed Index reflect market sentiment changes. These insights contribute to a deeper understanding of behavioral finance by illustrating how psychological factors, such as investor sentiment and the bandwagon effect, interact with digital asset markets. From a practical perspective, the results emphasize the importance of recognizing these interdependencies for policymakers and market participants striving to foster innovation in the rapidly evolving NFT ecosystem. By aligning with the transformative potential of Blockchain and DeFi, this study provides strategic insights for optimizing resource allocation, enhancing market efficiency, and shaping regulatory frameworks within innovative financial landscapes.
Alisa Kalacheva, Pavel Kuznetsov, Igor Vodolazov, Yury Yanovich
The rise in cryptoasset valuations and the ease of creating new tokens have spurred an increase in illicit activities within the market. Decentralized exchanges (DEX) facilitate the trading of a vast array of tokens, including those with minimal liquidity, amplifying the risk of fraudulent schemes. Fraudulent practices take various forms, including counterfeit tokens, rug pulls, and pump-and-dump schemes, all lacking functional innovation and relying heavily on aggressive social media marketing. This study contributes to the identification and profiling of deceitful tokens on DEX platforms. Our approach involved compiling on new tokens with an active trading start and attracted competition to buy them in first blocks spanning multiple years from the Ethereum blockchain, tracking all associated purchase and sale transactions. Our analysis revealed that Uniswap V2 predominantly hosts the trading of new tokens, with an alarming discovery that over 98% of tokens minted daily exhibit fraudulent characteristics. Subsequently, a machine learning model was developed to predict the likelihood of a rug pull occurring shortly after trading commencement. Although the dataset labeling methodology and detection problem statement are exploratory, we demonstrate the economic significance of the proposed approach within trading pipeline. The findings highlight the importance of identifying fraudulent activities and emphasize the need for collaboration between decentralized exchanges and regulatory bodies to mitigate financial losses for investors.
The environmental impact of cryptocurrencies has attracted increasing scrutiny, largely due to the high energy consumption of blockchain networks. However, empirical research on the causal relationship between cryptocurrency trading activity and carbon emissions remains scarce. This study addresses this gap by analysing the dynamic interplay between cryptocurrency trading and COâ emissions for Bitcoin, Ethereum, and Binance Coin, using monthly data from January 2015 to September 2024. Employing the Toda-Yamamoto augmented Granger causality approach, we apply logarithmic transformations to ensure data stationarity and address integration and endogeneity concerns. Our results reveal a bidirectional Granger causality between Bitcoin trading and COâ emissions, suggesting a feedback loop between market activity and environmental impact. For Ethereum, we find a similar albeit weaker bidirectional causality from trading to emissions, while no significant causal link is detected for Binance Coin, likely reflecting its more energy-efficient consensus mechanism. These findings highlight the disproportionate environmental burden of proof-of-work cryptocurrencies and underscore the need for targeted regulatory responses. We recommend the adoption of carbon-sensitive crypto policies, such as mandatory energy usage disclosures and incentives for transitioning to sustainable consensus mechanisms. This study advances the environmental finance literature by providing robust empirical evidence on the links between digital asset markets and carbon emissions.
Constructing an effective asset allocation strategy requires building well-diversified portfolios that maintain robust performance beyond the sample data. The classical Markowitz portfolio optimisation, while widely used, is known to suffer from issues such as estimation errors and sensitivity to multicollinearity, which can significantly distort the allocation process and reduce performance reliability. In order to surmount the aforementioned challenges, the incorporation of Machine Learning echniques, specifically Ridge regression, into the portfolio creation process has been effected. This has resulted in the provision of a hybrid model that combines the strengths of Markowitz optimisation and Ridge regression. The integration of these approaches within the hybrid model serves to mitigate the prediction risks while maintaining the diversification benefits inherent to the Markowitz framework. The model was trained using an 80/20 split and cross-validation was employed to prevent overfitting. The findings indicate that this integrated approach attains the maximum Sharpe ratio, thereby significantly enhancing risk-adjusted returns and portfolio stability when applied to cryptoasset returns. The findings emphasise the merits of integrating classical optimisation methodologies with machine learning to develop more robust and adaptive asset allocation strategies. By analysing the impact of high-volatility cryptoassets on portfolio performance, it makes important contributions to both the literature and practical portfolio strategies for investors.
Senior Financial Markets Dealer, Nassau, The Bahamas, Vladyslav Yakymashko
This article investigates the phenomenon of volatility clustering in the cryptocurrency markets, focusing on Bitcoin (BTC) and Ethereum (ETH), through empirical time-series analysis. The study employs quantitative methods, including GARCH modeling, to identify persistent patterns in the price fluctuations of the two leading digital assets. The analysis is based on trading data over an extended period, encompassing both phases of high market turbulence and periods of relative stability. Adopting an interdisciplinary approach that integrates behavioral finance, econometrics, and financial market theory, particular attention is given to identifying autocorrelation, memory effects, and the structure of market shocks. The findings demonstrate that volatility clustering in BTC and ETH significantly differs from similar phenomena in traditional financial markets, largely due to their speculative nature, asset novelty, and the influence of both institutional and retail participants. The identified patterns enhance risk profiling for crypto assets and may be applied in hedging strategies, automated trading algorithm development, and investment portfolio optimization. Additionally, the study highlights the importance of accounting for both micro- and macroeconomic factors influencing market behavior. The article is intended for researchers in digital finance, risk managers, analysts, investors, and anyone examining unstable assets in conditions of high uncertainty and a rapidly changing informational landscape.