Abstract This study uses high-frequency price data to analyze risk connectivity among 15 cryptocurrencies, focusing on moments such as volatility, skewness, kurtosis, and jumps during the pre-COVID-19 era, the COVID-19 epidemic, and Russian-Ukrainian tensions. The results indicate that Ethereum Classic is a major shock transmitter in all periods, and this effect becomes more pronounced during geopolitical crises. In contrast, Stellar, Tezos, and Tron are important shock absorbers, particularly during market volatility. Jump risk analysis confirms the dominance of Ethereum Classic and its capacity to increase spillover risks during crises. For higher-order moments, the findings reveal that Bitcoin, Ethereum, and Dash are significant transmitters of skewness spreads, whereas Dash and Eos are significant transmitters of kurtosis spreads. Jump risk analysis confirms the dominance of Ethereum Classic and its capacity to increase spillover risks during crises. These findings highlight the need for targeted risk management strategies adjusted to cryptocurrency market dynamics.
This study aims to analyze the volatility dynamics and spillover phenomena among major crypto assets (Bitcoin, Solana, and Ethereum) and their relationship with the Jakarta Composite Index (JCI), a proxy for the Indonesian capital market. In the era of digital financial integration, the link between speculative crypto asset markets and conventional stock markets is a crucial issue for financial system stability. This study uses daily price time series data for the period 2020-2025. The analysis was conducted using the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model and the Diebold-Yilmaz spillover index approach to measure the magnitude of shock transmission between markets. The results indicate significant volatility transmission among the three crypto assets, with Bitcoin remaining the primary source of volatility. Furthermore, this study finds an increasing dynamic correlation between the global crypto market and the Indonesian capital market during periods of economic uncertainty. These findings have important implications for investors in portfolio diversification strategies and for Indonesian regulators in monitoring systemic risks originating from digital assets.
This research examines 42 countries and investigates the relationship between geopolitical risk and global non-fungible token (NFT) investor attention. We use Google search volumes related to NFTs across different regions as a proxy for such attention. Our findings indicate that geopolitical risk positively impacts global NFT investor attention, suggesting that investors in countries with higher geopolitical risk may pay more attention to the NFT market. We further explore the effects across different NFT segments and find that geopolitical risk particularly influences investor attention in the metaverse segment. This positive nexus is further amplified during the Russia-Ukraine war and the COVID-19 pandemic.
I replicate and extend the cross-sectional trend-factor methodology of Liebi, Stulz, and Tsyvinski (2024) on a contemporaneous out-of-sample period and a liquidity-restricted coin universe. Using 141 USDT spot pairs over 128 weekly observations from November 2023 to April 2026, an Elastic-Net cross-sectional regression aggregating 29 technical indicators generates a long-short portfolio with a mean weekly return of 3.82% (Newey-West t = 5.03) and an annualized Sharpe ratio of 4.54. The strategy delivers market-neutral alpha of 3.82% per week (t = 7.09) with a CAPM beta of 0.020. Three findings warrant emphasis. First, value-weighting destroys the alpha entirely, confirming concentration in smaller, dispersed names. Second, twelve of the top fifteen Elastic-Net coefficients are negative, indicating that the underlying pattern is short-term reversal rather than trend continuation. Third, returns are heavily regime-dependent, with Sharpe ratios near 1.0 in trending markets and above 7.0 in dispersive regimes. Cross-sectional dispersion-harvesting alpha persists in cryptocurrency markets, but its empirical realization is sharply sensitive to universe liquidity, weighting scheme, rebalance horizon, and market regime.
The financial world stands witness to newer investment alternatives like digital assets (cryptocurrencies and non-fungible tokens [NFTs]) and the energy market (dirty energy and clean energy). Despite these advancements, their relationship has received little scholarly attention. This study illuminates dynamic interconnections among these two dominant and novel asset classes from 31 December 2019 to 21 January 2026 using the quantile connectedness approach. The results demonstrate increased connectedness during periods of turmoil. Oil and gas remain constant as net receivers, and Decentraland and Theta as net transmitters. Interestingly, clean energy indices remain net receivers during normal market situations but become net transmitters during extreme ones, signalling a good diversifying potential. Cryptocurrencies tend to be net receivers at the median and upper quantiles but shift to net transmitters at lower quantiles. The results signify an increasing technology and sustainability-driven economic shift. The current study contributes to the existing literature by being one of the preliminary studies to check the relationship between these two prominent asset classes and holds important implications for various stakeholders. It offers insights for investors and corporates to focus on technology and clean energy markets while advising policymakers and regulators to roll out policies and regulations that streamline these emerging sectors.
This paper investigates the resilience and dynamic behavior of energy-conserving cryptocurrencies (ECCs) during two major global crises: the COVID-19 pandemic and the RussiaâUkraine conflict. Unlike traditional proof-of-work (PoW) assets, ECCsâprimarily proof-of-stake (PoS) and low-energy blockchain tokensâare increasingly promoted as sustainable digital alternatives. Using a balanced panel of major ECCs across 10 countries with cryptocurrency markets from January 2019 to December 2023, we apply a panel ARDLâPMG model combined with panel causality tests and structural break analysis to examine the long- and short-run effects of global uncertainty on ECC returns and volatility. Our findings show that ECCs exhibit stronger crisis resilience compared with high-energy cryptocurrencies, with limited long-run exposure to pandemic shocks but moderate sensitivity to geopolitical tensions following the RussiaâUkraine conflict. COVID-19 uncertainty has a short-run negative pressure on ECC markets, whereas geopolitical risk (GPR) driven by the conflict generates asymmetric responses. Cross-country results reveal that ECC markets in technologically advanced, energy-transition economies (EU, Singapore, UAE) exhibit greater stability than those in emerging markets. These findings highlight the potential role of ECCs in sustainable finance, offering policymakers, investors, and regulators insights into the feasibility of promoting energy-efficient digital assets amid extreme global uncertainty.
This study examines dynamic interdependencies and risk transmission among major cryptocurrencies and traditional financial assets, including Bitcoin, Ethereum, U.S. equities, and gold, over the period 2017â2024. Particular attention is given to the structural shift associated with the 2024 U.S. spot Bitcoin exchange-traded fund (ETF) approval, which marked a significant milestone in the institutionalization of cryptocurrency markets. Using daily data, the analysis distinguishes volatility-driven co-movement from structural spillover effects across markets. Dependence structures are modeled using tail-sensitive Student-t copulas applied to GARCH-filtered returns to capture nonlinear and extreme co-movements, while a vector autoregressive framework combined with generalized impulse response functions and DieboldâYilmaz connectedness measures is employed to evaluate order-invariant shock transmission dynamics across pre- and post-ETF regimes. The results reveal three main findings. First, cryptocurrencies display strong internal dependence and short-horizon contagion, with Bitcoin consistently acting as the dominant transmitter of shocks to Ethereum over an approximately three-day transmission window. Second, linkages between cryptocurrencies and equity markets remain moderate and largely regime-dependent rather than indicative of persistent structural spillovers. Third, gold remains weakly connected throughout the sample, maintaining its role as a diversification asset. Portfolio analysis further indicates that including Bitcoin can reduce portfolio variance by 4â7% and Value-at-Risk by up to 5%, although economic gains are sensitive to transaction costs. Overall, the findings suggest that cryptocurrencies function as a partially segmented asset class, offering conditional diversification benefits despite increasing institutional adoption.
Javier Cifuentes-Faura, Hind Alofaysan, Magdalena Radulescu, Buhari DoÄan
This study employs novel decomposed connectedness and portfolio analysis to assess the dynamic spillover effects among carbon finance, artificial intelligence, green energy markets, and bitcoin. The findings indicate that the average total connectedness index is 62%, especially during extreme market conditions. The decomposition of this measure into contemporaneous and lagged connectedness reveals that 56% of the metric can be attributed to contemporaneous dynamics. The portfolio exhibits high Hedging Effectiveness, particularly in extreme market conditions, suggesting that green assets can mitigate risks during periods of financial and geopolitical turmoil. The outcome shows that investments in Bitcoin and technology-related assets often yield the highest returns from 2018 to 2023. Based on the findings, relevant investment policies have been suggested for investors and policy decision-makers.
Type of the article: Research ArticleAbstractCryptocurrency markets are highly volatile, making price prediction a complex yet essential task for investors, financial engineers, and institutions. The purpose of this study is to evaluate whether Bayesian optimization of technical indicator parameters significantly improves the forecasting performance of Long Short-Term Memory (LSTM) models compared to baseline configurations. The study used daily Bitcoin and Ethereum price data from January 2016 to September 2025. Six technical indicators representing trend, momentum, volatility, and volume-based technical indicators are constructed and dynamically optimized through Bayesian optimization. The optimized indicators are then used as inputs to an LSTM forecasting framework. The study found that the baseline LSTM model achieved moderate predictive accuracy, where Ethereum outperformed Bitcoin. After optimization, both models exhibited improved performance, reducing the forecasting error for Bitcoin by 36.4% and for Ethereum by 12.2%. LSTM model with Bayesian optimized indicators showed a higher forecasting accuracy as compared to the baseline model, with 32% and 18.6% improvements for Bitcoin and Ethereum, respectively. These findings suggest that combining optimized technical indicators with LSTM models enhances predictive power in cryptocurrency markets. The approach offers a robust forecasting framework for traders, analysts, and algorithmic systems in high-volatility environments.AcknowledgmentâThis work was funded by the Deanship of Scientific Research, Vice Presidency for Graduate Studies and Scientific Research, King Faisal University, Saudi Arabia [Project No. KFU261690].â
Abstract This study proposes a methodological strategy composed of econometric techniques and time series modelling to analyse the dynamic asynchrony between Bitcoin and a basket of traditional sustainable financial assets and emerging markets over a 10-year period marked by major economic and financial changes. The centrepiece of this proposal is the Relation Index that combines vector autoregression and detrended cross-correlation analysis to capture linear and nonlinear dependencies, causality, and time-scale sensitive correlations. Thus, this research fills existing gaps in understanding cross-market interdependencies by integrating cryptocurrencies, sustainability indices, and emerging economies into a rigorous multivariate time series framework. Sustainability indices, emerging markets and Bitcoin have shown a growing correlation since 2020, with both interest rates and Bitcoin having strong autoregressive components. The findings indicate that emerging market equities have undergone a structural shift towards synchronisation with global risk assets, with a correlation index that frequently exceeds 0.6 in periods of systemic stress. This evolution highlights the decline in the advantages offered by diversification in developed and developing economies in a complex and interrelated financial environment.
Bitcoin and major precious metals are frequently discussed as hedges against equity drawdowns, inflation surprises, and policy uncertainty, which implicitly assumes a degree of functional equivalence in their risk behavior. Existing work remains limited in assessing high-dimensional dependence structures in the Bitcoin and precious metals system, without relying on bivariate conditional risk measures or restrictive copula frameworks. This study therefore aims to quantify bilateral and multivariate tail dependence and systemic spillovers between Bitcoin and selected precious metals and to identify the best-performing multivariate tail-risk specification, with model comparison conducted using AIC and BIC. The analysis uses 3,665 daily observations of adjusted closing prices spanning January 2013 to September 2024, sourced from Yahoo Finance. Marginal returns are fitted with an ARFIMAâFIGARCH skewed-t model, while cross-asset tail dependence is estimated via vine-copula quantile regression (C- and D-vines) using a 252-day rolling window (one-day step) with 10,000 copula simulations. Results indicate that Bitcoin exhibits substantially larger downside systemic contributions than precious metals, whereas gold displays the smallest systemic risk profile. Across information criteria, the D-vineâbased SCoVaR specification provides the best overall fit, indicating that vine-based multivariate tail-risk measures better characterize systemic spillovers between the cryptocurrency and traditionally defensive assets under extreme market conditions. These results motivate future research on broader cryptocommodity networks and macro-financial conditioning, while practitioners and regulators can use the D-vine SCoVaR to monitor and mitigate downside spillovers in mixed-asset portfolios.
Abstract: This study investigates the dynamic relationships between Bitcoin, oil prices, and the US dollar (USD) using a Vector Autoregressive (VAR) model. Utilizing daily data from 2018 to 2023, the analysis reveals that both Bitcoin and oil prices exert significant short-term impacts on the USD, though these effects diminish over the long term. Bitcoin, characterized by its high volatility and safe-haven attributes, serves as an alternative asset during periods of economic uncertainty, while oil prices influence the dollar through trade flows and inflationary pressures. The findings highlight the transient nature of these interactions, with Bitcoin and oil acting as short-term pressure factors on the USD. These insights are crucial for investors and policymakers in managing risks and optimizing strategies in a volatile financial environment. This study contributes to the literature by providing empirical insights into the interconnectedness of cryptocurrencies, commodities, and currencies, offering valuable implications for financial decision-making. Keywords: Bitcoin, Oil Prices, US Dollar (USD), Vector Autoregressive (VAR) Model, Cryptocurrencies, Exchange Rates, Safe-Haven Assets JEL Classification Number: C32, E44, G15, Q43
The amount of international capital invested in sustainability-focused investments and decentralized financial technologies has been growing fast. Thus, this research focuses on the transmission of volatility and optimal portfolio composition among decentralized finance (DeFi) assets, S&P renewable energy and technology market indices, and conventional energy commodities for the period from March 15, 2018, to August 30, 2024. The sample period was divided into three sub-periods to examine the impact of COVID-19, which increased in parallel with the adoption of DeFi and a focus on sustainability: pre-COVID, during-COVID, and post-COVID. This research utilizes the Diebold-Yilmaz and BarunĂk-KĆehlĂk techniques for time-and frequency-domain analyses, and the Dynamic Conditional Correlation model for portfolio optimization. First, the findings reveal that DeFi tokens (sustainable markets) (brown investments) display moderate (high) (very low) internal connectedness. Second, DeFi tokens demonstrate very low volatility connectedness with both sustainable and brown markets, which suggests strong diversification effects. Third, volatility connectedness among sustainable markets and conventional energy commodities is equally low. Fourth, sustainable markets (conventional energy commodities) make the highest (lowest) contribution to total volatility connectedness, and they operate as net transmitters (receivers) of volatility. Moreover, the total volatility connectedness is 33.7%, which is relatively low, suggesting significant opportunities for diversification of investment portfolios. Furthermore, the outcomes for optimal portfolio weights present greater allocations to green markets compared to conventional energy commodities and DeFi assets, revealing an escalating global transition toward sustainability. Additionally, COVID-19 significantly influenced volatility transmissions and portfolio allocations.
Abstract Dynamics of financial contagion rapidly and drastically transformed by diversifying the investment preferences. Eventually increased diversification in the investment environment coupled with successive global events induced more complex and non-linear connections between the traditional and emerging markets. In this respect, this research explores the dynamic, asymmetric, and non-linear volatility transmissions among the Decentralized Finance (DeFi), Commodity, Energy, Technology, and Clean Energy Markets by incorporating Long Short Term Memory (LSTM) into the Time Domain of Time Varying Parameters Vector Auto Regression (TD-TVPVAR) model to eliminate the shortcomings of the former studies. Results compare the outputs of the Frequency Extension of TVPVAR (FC-TVPVAR) and LSTM-TVPVAR methods and verify the achievements of the new methodology. Consequently, new approach identify Bitcoin (BTC), gold, and oil markets as the primary sources of volatility, since clean energy market is determined to be the only significant destination of risk. Finally, prediction accuracy and the reliability of the incorporated model are validated by performance metrics and the achievements of the new approach are verified by bootstrapping test results.
This study examines short-term return forecasting for Bitcoin, Ethereum, and Litecoin over 2020â2024, comparing autoregressive benchmarks with Kitchen Sink and VARX-type models using point and density accuracy measures supported by DieboldâMariano and Model Confidence Set inference. The results demonstrate that the AR(1) benchmark and parsimonious specifications incorporating cryptocurrency-specific variables consistently outperform the more elaborate linear frameworks considered, while the inclusion of macro-financial predictors offers limited benefits. Findings highlight the robustness of autoregressive dynamics for short-term cryptocurrency forecasting and underscore the importance of parsimony over model complexity. These results are consistent with a market environment characterised by high structural uncertainty, sentiment-driven trading and rapidly shifting regimes, in which additional macro-financial information contributes little to forecastability beyond short-run return momentum and crypto-specific volatility.
Purpose The primary purpose of this research is to empirically analyze the co-movement, nonlinear dynamics, and spillover effects among non-fungible tokens (NFTs) and decentralized finance (DeFi) tokens, carbon exchange-traded funds (ETFs). The study aims to quantify these interactions, especially during major global crises, to derive practical implications for constructing sustainable and diversified investment portfolios. It seeks to provide a quantitative foundation for environmentally conscious investors to navigate the risks and opportunities at the intersection of digital finance and sustainability, addressing a significant gap in the existing literature. Design/methodology/approach This study employs a quantitative approach using advanced econometric models to analyze the daily returns of NFTs, DeFi tokens and Carbon ETFs. The methodology is centered on time-frequency analysis to capture dynamic relationships. Key methods include wavelet coherence (WTC) to identify co-movements across different time scales, partial wavelet coherence (PWC) to isolate direct linkages by controlling for systemic factors and wavelet correlation to examine how these relationships evolve over various investment horizons. This robust framework moves beyond traditional linear models to analyze complex, nonlinear market dynamics. Findings The relationship between digital assets and carbon ETFs is profoundly dynamic, event-driven and frequency-dependent. Co-movements, weak in the short term, intensify dramatically during global crises like the COVID-19 pandemic and geopolitical conflicts. The correlation strengthens progressively as the investment horizon lengthens, indicating carbon ETFs serve as a strong proxy for long-term systemic factors. PWC analysis confirms these are genuine, direct linkages, not merely spurious correlations, highlighting the true interconnectedness of these markets during periods of global instability. Research limitations/implications This study is limited by its focus on a specific set of assets and a defined time period (2020â2024); therefore, findings may not be generalizable to all market conditions or digital assets. The use of CRBN and SMOG as proxies for the carbon market may not capture all nuances of environmental finance. Future research could expand this framework by incorporating other financial markets, such as bonds and commodities, or by applying regime-switching models like SETAR to further explore nonlinear dynamics and enhance the robustness of the findings. Practical implications For environmentally conscious investors, this study provides a quantitative foundation for building climate-aligned portfolios. The findings demonstrate that integrating carbon ETFs into a digital asset portfolio is a sound risk management strategy that enhances diversification and hedges against both market volatility and potential regulatory risks tied to blockchainâs carbon footprint. The results suggest a strategic allocation approach: utilizing stablecoins as portfolio anchors, carefully managing exposure to central shock transmitters and incorporating carbon ETFs for long-term stability and hedging. Social implications This research provides a data-driven roadmap for aligning the burgeoning field of digital finance with pressing sustainability goals. By demonstrating how to construct portfolios that are both financially robust and environmentally responsible, it addresses the significant environmental concerns surrounding blockchain technology. This contributes to a more sustainable financial ecosystem, offering a pathway for investors to participate in innovative digital asset markets while actively managing and hedging against their carbon footprint, thereby promoting greater corporate and social responsibility in finance. Originality/value This paperâs originality lies in its comprehensive empirical analysis of the co-movement and nonlinear dynamics among the specific triad of NFTs, DeFi tokens and carbon ETFs â an intersection that remains largely unexplored. By applying advanced wavelet-based methodologies, the study provides novel, actionable insights into the event-driven and frequency-dependent nature of their interconnectedness. It successfully bridges the gap between digital finance and sustainability, offering a unique, data-driven framework for constructing resilient, next-generation portfolios that are both financially sound and environmentally conscious.
Abstract Purpose â The study evaluates the connectedness among the less riskier Digital Assets by investigating the functions of gold backed cryptocurrency alongwith Fan Tokens, Non-fungible Tokens and Real estate tokens, as a new alternative asset class that can be utilized by portfolio managers and investors alongwith policy makers. Design/methodology/approach â This study uses Quantile Vector Auto Regression analysis to measure the quantile cohesiveness among Islamic Cryptocurrencies, Non-Fungible Tokens, Fan Tokens and Real Estate Tokens, recommended by Ando et al., (2022) given extreme quantiles, which specify tail features among different markets performing under extreme conditions. The quantile cohesiveness proposed by Ando et al. (2022) is the blend of quantile vector auto regression with Diebold and Yilmaz (2012) methodology of spillovers for measuring the cohesiveness of the volatilities of markets for extreme higher (95th) and extreme lower (5th) quantiles. Findings â The findings of the QVAR divides spillover in two market condition i.e. median and extremes. In median market condition or we can say normal conditions findings of QVAR shows that Fan token is the major transmitter of shocks while Islamic crypto like X8X is major receiver of the shocks. In extreme condition the major transmitter remains the same i.e. Fan Tokens but major receiver of shock is Real Estate Tokens. Originality/ Value: â Study offer valuable insights to policy makers, portfolio managers and individual investors. For instance study enable the portfolio managers and investors to understand spillovers among Islamic Crypto, Non-Fungible Tokens, Fan Tokens and Real Estate tokens, which will help them in making suitable portfolios. By investigating the function of Islamic gold-backed cryptocurrencies as a new and alternative asset class that can be utilized by both portfolio managers and investors, looking to invest in Islamic Products, to lower their risk of investment. Research Implications: - This study brings novel insight for portfolio optimization and diversification. The findings of this study will have implications for global investor, researcher and policy makers.
This study aims to comparatively examine the relationships between Bitcoin and Ethereum's energy consumption and price dynamics. Using daily frequency data, Augmented Dickey-Fuller (ADF), Phillips-Perron (PP), ARDL cointegration tests, and TodaâYamamoto causality analysis were applied to evaluate the effects of cryptocurrency markets on energy demand from both short-term and long-term perspectives. The analysis results indicate that there is a long-term cointegration relationship between energy consumption and prices for Bitcoin and a unidirectional causality from prices to energy consumption. In contrast, ARDL boundary test results for Ethereum revealed no long-term relationship, and causality analysis also failed to detect any directional causality between price and energy consumption. This indicates that with Ethereum's transition to a Proof-of-Stake mechanism, energy consumption has become independent of price movements. The findings reveal that the effects of cryptocurrency markets on the energy economy vary according to technology-specific structural characteristics.
Ifran Khan, Huangbao Gui, BiJia Li, Chin Man Chui · 5 authors
The Diebold and Yilmaz (2012) and BarunĂk and KĆehlĂk (2018) are two complementary models used in this study to examine the transmission of volatility spillover among the five precious metals (gold, silver, platinum, palladium, and rhodium); the top five cryptocurrencies (bitcoin, ethereum, tether, ripple, and binance coin); two green equities (NASDAQ OMX green energy and S&P global clean energy indexes); and two physical and transition climate risk indexes (PRI and TRI). The analysis spans daily data from January 2018 to December 2023, covering multiple crises. One key contribution is offering new insights into asset interactions with transition and physical climate risks based on textual analysis established by Bua et al. (2024). We conclude that volatility spillovers explain 40.3% of market uncertainty. The largest transmitters include ethereum (72.17%), bitcoin (64.65%), silver (52.42%), and XRP (49.18%), while TRI and PRI also play considerable roles. Ethereum, bitcoin, silver, XRP, rhodium, and clean energy emerged as net transmitters, while palladium, TRI, PRI, USDT, gold, BNB, the green economy, and platinum act as net receivers. Short-term spillovers (39.15%) dominate medium-term (18.27%) and long-term (20.88%), implying that short-term shocks pose greater risks to investors. The climate-related risks demonstrate distinct transmission mechanisms, with transition risks (TRI) responding to broad market movements while physical risks (PRI) propagate through more specialized channels. Our study suggests that investors should closely monitor cryptocurrencies and green assets in the short term, approach gold and stablecoins with caution in the medium term, and consider long-term allocations to rhodium and clean energy assets.
Ceyda Yerdelen Kaygın, Musa GĂŒn, Osman Nuri Akarsu, HaĆim BaÄcı · 5 authors
Forecasting cryptocurrency prices is challenging due to extreme volatility, nonlinear dynamics, and frequent structural shifts in digital asset markets. While recent research increasingly applies deep learning architectures, the predictive advantage of highly complex models in noisy financial environments remains uncertain. This study evaluates the forecasting performance of shallow and deep learning approaches by comparing Support Vector Machines (SVM), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models, along with hybrid configurations (GRU + SVM, LSTM + SVM, and GRU + LSTM). Using daily data spanning from 1 October 2020 to 23 September 2025 for five major cryptocurrenciesâBitcoin, Ethereum, Binance Coin, Solana, and Rippleâthe models are estimated within a consistent framework and assessed using out-of-sample performance metrics, including MAE, MAPE, MSE, and R2. The results indicate that greater algorithmic complexity does not necessarily improve forecasting accuracy. In several cases, the parsimonious SVM model outperforms deep neural network architectures, particularly for highly volatile assets, while hybrid models fail to provide systematic improvements and sometimes amplify prediction errors. SHapley Additive exPlanations analysis further shows that immediate price-based variables dominate predictive power, whereas many lagged technical indicators contribute relatively limited explanatory value. Overall, the findings underscore the importance of algorithmic parsimony, suggesting that simpler machine learning models may deliver more robust forecasts in highly volatile cryptocurrency markets.