Large language models (LLMs) have shown strong potential for financial analysis and trading, but direct trading remains challenging because the predictive capabilities required can vary across assets, decision fields, and market conditions. Existing LLM-based trading systems either coordinate human-defined external experts or adopt conventional internal Mixture-of-Experts (MoE) routers that do not directly evaluate how individual experts contribute to trading decisions. Moreover, these routers receive no direct signal indicating when an inactive expert has become more suitable as market conditions change. We find that native router scores poorly reflect how much individual experts improve trading decisions, frequently leaving better alternatives unselected. We further reveal that token-specific expert usefulness exhibits a compact low-dimensional structure. Based on these findings, we propose TradingMoE, a trading-oriented sparse MoE that augments a frozen dense LLM with lightweight residual experts. We introduce a Query-Key router that represents the expertise required by each token under the current market context as a low-dimensional query and matches it with learnable expert keys. We further propose a sparse expert selection update mechanism that samples a few inactive experts during training and estimates whether they should replace the weakest expert in the current Top-k route. This mechanism enables the router to update expert selection as market conditions change while preserving sparse computation. Experiments against 22 baselines on stock and cryptocurrency markets show that TradingMoE improves cumulative return over the best-performing baselines by 30.89% and 30.7%, respectively. Rolling paper-trading experiments further demonstrate that its advantage persists under forward-only deployment.
Crypto currency is one of most interesting financial innovation of 21st century. Crypto currency trading not only involve financial literacy while trading but also there are psychological factors affecting the decision of traders. Keeping in view the psychological factors and investors’ decision, this research study is designed to investigate the complex interplay between psychological triggers and market dynamics in the cryptocurrency sector in Pakistan, specifically examining how these elements coalesce to drive investor behavior and market volatility. While traditional financial models often attribute asset fluctuations to technological or fundamental shifts, this study posits that cryptocurrency markets are fundamentally driven by human perception and emotional reactivity. Utilizing a quantitative methodological approach, data was collected from a sample of 175 experienced traders to analyze the impact of emotional states, market sentiment, and behavioral discipline on trading outcomes. The empirical results, derived through multiple linear regression analysis, reveal that the model possesses a high level of explanatory power, accounting for 56% of the variance in emotional trading behavior (R2=0.56R2=0.56). Market sentiment emerged as the primary determinant of impulsive trading (β=0.48β=0.48), demonstrating that external social cues often exert a stronger influence on decision-making than internal emotional states. Among specific psychological variables, Fear, Uncertainty, and Doubt (FUD) were identified as the most significant predictors of rash choices (β=0.34β=0.34), while the Fear of Missing Out (FOMO) also demonstrated a substantial, though secondary, effect (β=0.21β=0.21). Conversely, the study found that trading experience and the application of systematic strategies serve as vital moderating factors that decrease emotional reactivity and enhance behavioral stability (β=−0.19β=−0.19). The findings contribute to the fields of behavioral finance and digital economics by illustrating that the volatility inherent in digital assets is a systemic byproduct of individual psychological biases aggregated through digital narratives. The research concludes that achieving a sustainable financial ecosystem requires moving beyond purely technical regulations. Instead, it advocates for the implementation of behaviorally-informed safeguards, such as algorithmic "cooling-off" periods and sentiment-aware trading tools, to mitigate the risks associated with reactive investing. Ultimately, this work provides a blueprint for a more resilient digital financial future by prioritizing human factors in market governance.
This study investigates whether the macroscopic statistical maturity of cryptocurrencies implies dynamical equivalence with traditional equity markets. We analyze high-frequency data (2020--2025) using the Complexity--Entropy Causality Plane (CECP) and directed horizontal visibility graphs (directed HVG) to uncover complex temporal patterns and time-directed structures in the return series. While conventional stylized facts show striking convergence across all assets, structural diagnostics reveal a compelling paradox: cryptocurrencies appear more locally random than the equity benchmark during ordinary periods, yet exhibit significantly stronger directional time-irreversibility around high-visibility return events. The absolute-return results show that large cryptocurrency fluctuations tend to begin abruptly and remain elevated afterward. Separate analyses of positive returns and negative-return magnitudes show that this pattern is shared across cryptocurrencies on the upside but varies across assets on the downside. We conclude that statistical maturity is only skin-deep; the underlying dynamical processes of mature cryptocurrencies remain fundamentally distinct from traditional benchmarks.
Volatility control converts risk estimates into portfolio exposure, yet existing approaches often rely on a fixed volatility estimator or a pre-defined control rule that may not adapt to changing market conditions. We propose VolRouter, a modular framework that formulates volatility control as state-conditioned routing over estimator-controller pairs. VolRouter first summarizes market conditions into a control-relevant state profile and then performs routing through three stages: state inference, switch review, and pair selection. The Router can be implemented using rule-based, learnable, or LLM-based decision modules, while portfolio actions remain generated by predefined control policies. We evaluate VolRouter across S&P 500, Multi-Asset, Bitcoin, and USDT volatility-control settings. VolRouter achieves the highest Sharpe ratio in three of four settings. On S&P 500, it improves Sharpe from 0.952 for RV + Naive Scaling to 1.222 while reducing maximum drawdown from 15.10% to 12.58% and daily CVaR from 1.76% to 1.32%. On Multi-Asset, it improves Sharpe from 1.498 to 1.540 and reduces CVaR from 1.56% to 1.18%. Bitcoin shows similar improvements in risk-adjusted performance, while USDT provides a boundary case where simpler state-aware selectors remain competitive. Ablation and sensitivity analyses show that the improvement comes from relative policy evaluation and selective persistent switching rather than simply expanding the policy library. These results suggest that volatility control can be viewed as a policy-selection problem when risk management requirements vary across market states.
Velian Prapatoni, Rizky Parlika, Firza Prima Aditiawan
Cryptocurrency markets are characterized by high volatility, rapid price fluctuations, and substantial uncertainty, creating challenges for investment risk interpretation. This study develops a descriptive risk-interpretation framework, rather than a price-prediction or decision-optimization model, by integrating multi-scale volatility analysis with technical indicators. A quantitative descriptive design was applied to approximately one year of historical hourly price data for Bitcoin and Ethereum, covering open, high, low, close, volume, and percentage change attributes. The data were chronologically sorted, numerically cleaned and normalized, transformed into log returns, and analyzed through rolling standard deviation. Volatility was estimated across three explicitly defined horizons: short-term 7-period, medium-term 30-period, and long-term 90-period rolling windows. Moving Average (MA), Relative Strength Index (RSI), and Average True Range (ATR) were then incorporated to contextualize trend direction, momentum, and fluctuation intensity. The results show that volatility is strongly horizon-dependent: short-term movements responded more sharply to market shocks, whereas longer horizons produced smoother risk patterns. Across the analyzed Bitcoin and Ethereum hourly series, the reported 42.3% short-term and 21.7% medium-term increases were calculated as relative differences against long-term rolling volatility during identified high-uncertainty intervals, not as predictive accuracy measures. These findings indicate that combining rolling volatility with MA, RSI, and ATR can improve the transparency of descriptive cryptocurrency risk assessment. The framework may support preliminary interpretation for novice or risk-averse investors, although it does not empirically test investor comprehension or subsequent decision quality.
Cryptocurrencies have emerged as a prominent asset class characterized by rapid price fluctuations, growing institutional participation, and continuing debate over whether their price movements are random or predictable. This study examines the randomness and weak-form market efficiency of the top ten cryptocurrencies by market capitalization—Bitcoin, Ethereum, Tether, Binance Coin, XRP, USD Coin, Solana, TRON, Dogecoin, and Hype liquid—using daily closing price data from April 2016 to March 2026 (subject to data availability for each coin). Daily log returns were tested using Descriptive Statistics, the Jarque–Bera test of normality, the Wald–Wolfowitz Run Test, and the Autocorrelation Test. The results show that daily returns for all selected cryptocurrencies are non-normally distributed, exhibiting excess kurtosis and skewness. The Run Test results indicate that seven of the ten cryptocurrencies—Bitcoin, Ethereum, Tether, Binance Coin, XRP, USD Coin, and Dogecoin—do not follow a random walk, while Solana, TRON, and Hype liquid exhibit randomness consistent with weak-form efficiency. However, the Autocorrelation Test reveals strong positive serial correlation across all ten cryptocurrencies, indicating that the market falls short of weak-form efficiency. The study concludes that the cryptocurrency market provides mixed and largely inefficient evidence with respect to the Random Walk Hypothesis, implying that historical price information may retain some predictive value for investors.
This study examines whether connectedness among green bond returns, Bitcoin returns, market uncertainty, and geopolitical risk differs systematically across market states. Using a Quantile Vector Autoregression (QVAR) framework, we estimate connectedness across lower-tail, median, and upper-tail market conditions. To assess statistical reliability, we report bootstrap confidence intervals and difference-based tests and benchmark the quantile estimates against a conventional mean-based VAR. The mean-based benchmark closely matches connectedness around the median quantile. By contrast, system-wide connectedness is significantly stronger in both tails than around the median, as confirmed by difference-bootstrap tests. The direct green bond – Bitcoin linkage is stronger in the lower tail than under normal market conditions, although its net direction is not robustly identified across quantiles. Directional spillovers suggest a more prominent transmitting role for market uncertainty around the median and for geopolitical risk in the upper tail, although these differences should be interpreted cautiously. Overall, the findings indicate that conventional mean-based analysis adequately characterizes connectedness under normal market conditions but cannot capture the pronounced intensification of connectedness observed in the tails.
This study investigates two questions relating to cryptocurrency market dynamics. First, whether a composite skew measure derived from MicroStrategy (MSTR) trading activity can predict future Bitcoin (BTC) and Ethereum (ETH) volatility. Second, whether Ethereum volatility exhibits reproducible structural properties consistent with established theories of volatility persistence and cascading shock dynamics. Using rolling out-of-sample testing, autocorrelation-adjusted significance testing, regime classification, shock-decay modelling, return-interval analysis, and earthquake-inspired cascade frameworks, the study finds no evidence that MSTR composite skew provides a useful forecasting signal. More broadly, no forecasting model tested outperforms naive benchmark models beyond horizons of approximately three to five days. However, several descriptive properties of Ethereum volatility appear robust, including volatility persistence, regime structure, extreme-event clustering, non-simple shock decay, and partially transferable aftershock dynamics. In particular, while Omori-style decay and the productivity law are supported, Bath's Law fails consistently, suggesting cryptocurrency volatility cascades may differ fundamentally from those observed in traditional financial markets. The findings contribute to the understanding of volatility organisation in digital asset markets while highlighting the difficulty of extracting persistent predictive signals from historical OHLCV
Victor Michelle, Natalie Michelle, Emilie Michelle, Elias Michelle
This paper introduces Prediction Assets — a fundamentally new class of financial instruments where the underlying asset is market consensus on probability itself. Unlike traditional prediction markets, where binary event contracts terminate abruptly upon resolution, Prediction Assets are engineered as perpetual financial instruments that evolve rather than expire. Upon event occurrence, the asset does not liquidate to zero or a fixed payout; instead, it programmatically transforms into a new functional asset form (such as a currency, index, or memory asset) via smart-contract-enforced conversion ratios, establishing an infinite lifecycle and continuous capital efficiency. Key Structural & Mathematical Contributions: Core Asset Pricing Model: Establishes the foundational pricing equation \(P_{asset} = P(E) \times M\) driven entirely by open order-book decentralized exchange (DEX/AMM) spot liquidity without reliance on subjective analytical oracles. Systemic Market Efficiency: Implements an exact arbitrage condition boundary constraint (\(\sum P_{asset,i} = M\)) to incentivize algorithmic market-making and eradicate structural price variance. Programmatic Post-Event Evolution: Introduces the deterministic conversion coefficient \(C(t, state)\) locked at genesis to handle automated migration profiles (Currency, Index, Memory, and Derivative states) with zero administrative discretion. Decentralized Governance: Outlines a 4-channel Multi-Chain Consensus Verification Layer (CVL) requiring a strict 3-of-4 quorum across official APIs, open-source replicas, academic mirrors, and market sentiment vectors. Regulatory Engineering: Delivers a comprehensive compliance analysis under the U.S. Securities Framework (Howey Test and Reves Test boundaries) and CFTC Event Contract frameworks, positioning the topology as a non-security utility asset. Prospective Implementation:The paper presents AIVA (Artificial Intelligence Valuation Asset) as the world's first prospective implementation tracking the global macro-consensus probability of achieving Artificial General Intelligence (AGI), which programmatically transforms into an operational settlement currency for autonomous multi-agent economic environments upon verification. Keywords: Prediction Assets, Probability Markets, Financial Instruments, AGI, AI Agents, Decentralized Finance, Synthetic Assets, Valuation Markets. Citation Note: This specification expands upon the sovereign fintech frameworks established in IP Stock Exchange v3.3-Evolution (DOI: 10.5281/zenodo.20687136).