This paper examines cryptocurrency shock transmission to financial markets and the macroeconomy using a Bayesian structural VAR with Pandemic Priors from 2015 to 2024. By affecting overall risk appetite, cryptocurrency price shocks generate positive financial market spillovers, accounting for 18% of equity and 27% of commodity price fluctuations. Real economic effects are significant in driving investment but remain limited, contributing only 4% to unemployment and 6% to industrial production variance. However, cryptocurrency shocks explain 18% of price-level forecast error variance at long horizons. Narrative analysis reveals sentiment and technology as primary shock drivers. These findings demonstrate cryptocurrency’s deep financial system integration with important inflation implications for monetary policy.
This study examines how decentralized finance (DeFi) platforms coordinate capital and liquidity through algorithmic mechanisms. Using reproducible on-chain data from the DeFiLlama API, the analysis constructs a structural econometric framework linking micro-level choice, production efficiency, and network spillovers. A sequence of models-conditional logit, nested logit, nested CES, and spatial error-captures how algorithmic inputs, digital capital, and inter-protocol dependencies shape efficiency and systemic behavior. Results show that DeFi protocols exhibit strong internal substitution between algorithmic and traditional inputs, while cross-protocol linkages produce measurable spatial effects in efficiency and growth. The findings highlight how decentralized systems can self-organize productive coordination without central intermediaries, contributing to ongoing debates on financial autonomy, digital liquidity, and algorithmic governance.
This paper investigates the intersection of artificial intelligence (AI) agents—autonomous software entities capable of adapting, learning, and executing multi-step operations—and decentralized finance (DeFi) ecosystems. It highlights how the adaptive decision-making capabilities, flexible governance frameworks, and data-driven optimization strategies of AI agents reshape market coordination and organizational architectures. Drawing on a qualitative analysis of 306 major crypto AI agents, the study introduces a typology that maps their diverse application areas, including algorithmic trading, portfolio management, sentiment-driven communities, and immersive entertainment. To further conceptualize the role of AI in decentralized governance, the paper develops a quadrant-based framework that distinguishes four archetypal system configurations: Traditional Decentralized Autonomous Organization (DAO) Tools, Maximally Distributed Agency, Closed Systems, and AI Dictatorships. These configurations, defined by varying degrees of autonomy and decentralization, reveal critical trade-offs between transparency, efficiency, adaptability, and control. This framework serves as a lens to theorize how AI agents reconfigure trust mechanisms, power dynamics, and decision-making processes in decentralized ecosystems. Grounded in economic and socio-technical theory, the paper positions AI agents as transformative intermediaries in tokenized environments. While demonstrating their capacity to streamline operations, enhance decision quality, and enrich user engagement, the study also addresses the governance risks posed by algorithmic control and systemic opacity. Taken together, the conceptual and empirical insights lay a foundation for ongoing interdisciplinary inquiry into the evolving role of AI agents in decentralized finance. • Introduces a typology of 306 AI agents across key DeFi application areas • Maps AI agent roles in trading, governance, community, and entertainment • Develops a governance framework for AI agent autonomy and decentralization • Shows how AI agents reduce transaction costs and reshape market structures • Highlights risks of opacity, misalignment, and centralization in DeFi AI use
Asad Ul Islam Khan, Rasim Özcan, Mohamed Abbas Ibrahim
In this paper, we use the Empirical Bayes estimation and multiple linear regression approach to examine the impact of the top 5 cryptocurrencies’ crash risks on the G-7 and China equity markets’ crash risks. MATLAB was used to calculate the crash risks, while Stata software was employed for the econometric analysis. Three crash risk measures are usedto validate the robustness of the results: (i) the relative frequency of the number of crash days in the market, (ii) the monthly returns’ skewness, and (iii) the down-to-up volatility. Our findings indicate that overall crash risks of the top 5 cryptocurrencies are positively related with G-7 and Chinese stock markets’ crash risk. This suggests that the crash risk transmits from the crypto to the equity markets and the crashes in crypto can serve as a predictor in the stock markets. Furthermore, there is a negative correlation between the historical crash risks of the G-7 stock market and the present crash risks of the same stock market. This suggests that past stock market crashes can serve as a predictive factor for assessing the current risk of a stock market crash.
Elie Bouri, Amin Sokhanvar, Harald Kinateder, Serhan Çiftçioğlu
• Reveals significant positive predictability in the stock market–cryptocurrency nexus. • U.S. tech and semiconductor stocks and Nvidia predict cryptocurrency returns and vice versa. • Mutual returns predictability is significant across several quantiles and lags. • It generally holds when controlling for the U.S. dollar index and treasury market. • A trading strategy based on the cross-quantilogram outperforms a benchmark strategy. This study examines the directional return predictability between the technology sector of U.S. stock market and three major cryptocurrencies (Bitcoin, Ethereum, and Dogecoin). Using daily data from August 7, 2015, to February 8, 2024, and the cross-quantilogram approach in both static and dynamic settings, the results reveal significant positive predictability in the stock market–cryptocurrency nexus. The technology sector, semiconductors subsector, and Nvidia Corporation exert predictive power over cryptocurrency returns and vice versa across several quantiles and lags. When controlling for the impact of other financial variables, namely, U.S. dollar and U.S. treasury markets, the return predictability holds, especially for the two largest cryptocurrencies, Bitcoin and Ethereum, which reflects their importance and tighter connections with the U.S. technology sector. A trading strategy based on the results of the cross-quantilograms outperforms a benchmark strategy (i.e., always long position in either stocks or cryptocurrency), which underlines the practical implications of our main findings, particularly in terms of the significant return interactions between U.S. technology/semiconductors stocks and large cryptocurrencies.
This study presents a novel methodology for multi-step Bitcoin (BTC) price prediction by combining advanced stacking-based architectures with temporal attention mechanisms. The proposed Temporal Attention-Enhanced Stacking Network (TAESN) integrates the complementary strengths of diverse machine learning algorithms while emphasizing critical temporal features, leading to substantial improvements in forecasting accuracy over traditional methods. Comprehensive experimentation and robust evaluation validate the superior performance of TAESN across various BTC prediction horizons. Additionally, the model not only demonstrates enhanced predictive accuracy but also offers interpretable insights into the temporal dynamics underlying cryptocurrency markets, contributing to both practical forecasting applications and theoretical understanding of market behavior.
The finite sample effect on the Hurst exponent (HE) of realized volatility time series is examined using Bitcoin data. This study finds that the HE decreases as the sampling period $Δ$ increases and a simple finite sample ansatz closely fits the HE data. We obtain values of the HE as $Δ\rightarrow 0$, which are smaller than 1/2, indicating rough volatility. The relative error is found to be $1\%$ for the widely used five-minute realized volatility. Performing a multifractal analysis, we find the multifractality in the realized volatility time series, smaller than that of the price-return time series.
Contemporary financial systems operate in complex environments marked by volatility, uncertainty, complexity, and ambiguity, which elevates the cost of trial and error and exposes the limits of siloed data and centralized control. Considering the complexity challenges for the legacy financial system, we propose the parallel financial systems, which are grounded in the theory of parallel intelligence and utilizes the ACP (Artificial systems, Computational experiments, and Parallel execution) methodology to conduct financial execution and resource coordination through the interaction and co-evolution of real-world and artificial systems. Based on this paradigm, we construct a corresponding technical architecture that integrates cutting-edge intelligent technologies represented by AI agents with decentralized technologies provided by blockchain, smart contracts and decentralized autonomous organizations (DAOs). To further demonstrate the applicability for the legacy enterprise, we detail the system workflow, from individual operation to group coordination, with an illustrative example of how the parallel financial systems are utilized along a project lifecycle. This work serves as a theoretical basis and design roadmap for verifiable, privacy-preserving, and interoperable financial intelligence.
The decentralized financial system that forms the basis of crypto assets is highly volatile and constantly changing, making the process of valuation one of the thorniest challenges of the modern-day finance sector. This study deals primarily with the analysis of several factors through which the value of cryptocurrency is determined and also seeks to stress how much caution is needed while addressing both risks and rewards. By employing multivariable and stochastic analyses, the study deconstructs the various factors at play in the bitcoin market. It is clear from the result that the volatile environment of the digital currency is a combination of one’s mood, new laws, and technological development. Thus, the findings underline the information that while it is possible to become an exception and make a brilliant rise at the financial top, there is also a large and often unpredictable downside involved. It is a valuable resource for the policymakers who have to come up with the legislation to regulate innovation without compromising the markets’ veracity, these results can be a useful tool for all investors who struggle to make the right decisions in the world of decentralized cryptocurrencies.
Forecasting the price of cryptocurrencies is a notoriously hard and significant problem, due to the rapid market growth and high volatility. In this article, we propose a methodology for predicting future values of cryptocurrency exchange rates by developing a Non-linear Autoregressive with Exogenous Inputs (NARX) prediction model that uses the most adequate external information. The exogenous variables considered are historical values of the exchange rate and a series of technical indicators. The selection of the most relevant external inputs is based on the computation of the mutual information indicator and estimated using the k-nearest neighbor method. The methodology employs a fine-tuned Long Short-Term Memory (LSTM) neural network as the regressor. We have used quantitative and trend accuracy measures to compare the proposed method against other state-of-the-art LSTM-based models. In addition, regarding the input selection process, the proposed approach was compared against the most commonly used one, which is based on the cross-correlation coefficient. A long series of experiments and statistical analyses proved that the proposed methodology is highly accurate and the resulting model outperforms the state-of-the-art LSTM-based models.
By taking Bitcoin, Ethereum, and Ripple as research objects, this paper applies the multifractal detrended partial cross-correlation analysis (MF-DPXA) to study the intrinsic cross-correlation between cryptocurrencies. Combining MF-DPXA and time-delay DCCA methods, we develop the removing factors time-delayed detrended cross-correlation analysis (R-TD-DCCA) to study the risk transmission direction between cryptocurrencies after removing the influence of common factors. The results show that after removing the influence of cryptocurrencies, the persistence of the cross-correlation between cryptocurrencies is enhanced, and the multifractal degrees of the cross-correlation between Bitcoin and Ethereum and between Ethereum and Ripple are increased, but the multifractal degree of the cross-correlation between Bitcoin and Ripple is weakened. However, after removing the influence of the S&P 500 index, the multifractal degree of the cross-correlation between cryptocurrencies has weakened. The Hurst exponent of local dynamic cross-correlation between cryptocurrencies is almost always greater than 0.5. With the increase in time delay, the risk of Bitcoin is mainly transmitted to Ethereum and Ripple, and the risk of Ripple is mainly transmitted to Ethereum. When removing the impact of the S&P 500 index, the short-term risk of Bitcoin is mainly transmitted to Ethereum and Ripple. The findings of this study have several implications for re-understanding the intrinsic interdependence structure and portfolios.
ABSTRACT Uniswap is a system of smart contracts on the Ethereum blockchain and is the largest decentralized exchange with a liquidity balance worth up to 4 billion USD and daily trading volume of up to 7 billion USD. It is a new model of liquidity provision, so‐called automated market making. For this new market form, we characterize equilibrium in the liquidity pools. We collect all 95.8 million Uniswap interactions and compare this automated market maker (AMM) to a centralized limit order book. We document absence of long‐lived arbitrage opportunities, and show conditions under which the AMM dominates a limit order market.
Purpose Cryptocurrency, an emerging asset class, is a virtual form of currency that uses cryptography for security and operates on decentralised networks based on blockchain technology. It offers both challenges and opportunities for investors, particularly in terms of diversification, risk management and potential returns. Considering this, the present study attempts to investigate the sentimental factors influencing cryptocurrency while unravelling the intricate interplay among these factors. Design/methodology/approach To achieve this, interpretive structure modelling (ISM) identifies the hierarchical model of critical sentimental factors, while Cross-Impact Matrix Multiplication Applied to Classification (MICMAC) explores their dependency and driving power. Analytic hierarchy process (AHP) is adopted to rank the drivers. Findings Findings reveal that the pandemic, war, religiosity and economic uncertainty are top-level factors dominantly shaping cryptocurrency trends. Simultaneously, Google Search Trends and Herding emerge as the most dependent factors, influenced by sentiments that emerged from other factors. Practical implications The study unpacks implications, acknowledges limitations and proposes avenues for future research. Originality/value By exploring the interactive interrelationships among identified sentimental factors through ISM-MICMAC analysis and ranking via the AHP, this paper will have a great influence while contributing towards this evolving field.
Cryptocurrencies fluctuate in markets with high price volatility, which becomes a great challenge for investors. To aid investors in making informed decisions, systems predicting cryptocurrency market movements have been developed, commonly framed as feature-driven regression problems that focus solely on historical patterns favored by domain experts. However, these methods overlook three critical factors that significantly influence the cryptocurrency market dynamics: 1) the macro investing environment, reflected in major cryptocurrency fluctuations, which can affect investors’ collaborative behaviors, 2) overall market sentiment, heavily influenced by news, which impacts investors’ strategies, and 3) technical indicators, which offer insights into overbought or oversold conditions, momentum, and market trends are often ignored despite their relevance in shaping short-term price movements. In this paper, we propose a dual prediction mechanism that enables the model to forecast the next day’s closing price by incorporating macroeconomic fluctuations, technical indicators, and individual cryptocurrency price changes. Furthermore, we introduce a novel refinement mechanism that enhances the prediction through market sentiment-based rescaling and fusion. In experiments, the proposed model achieves state-of-the-art performance (SOTA), consistently outperforming ten comparison methods in most cases. Our code and data can be found at https://github.com/aamitssharma07/SAL-Cryptopulse