发表机构
School of Art and Science University of Rochester; AGI Lab Beijing Institute of Mathematical Sciences and Applications（罗切斯特大学艺术与科学学院; 北京数学科学与应用研究院AGI实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对加密货币预测难题，提出结合FNO的MoFE框架，经比特币数据集实验，在T+1、T+5预测中达SOTA，缓解相位滞后，获更优DA、IC及高夏普比率的超额收益。
AI 中文摘要
由于内在非平稳性、突发制度转变和多尺度随机依赖，加密货币价格预测仍然是一项艰巨的挑战。传统深度学习模型往往难以捕捉复杂的潜在动态，经常导致持续的相位滞后预测。为解决这些限制，我们提出MoFE，一种将傅里叶神经算子（FNO）集成到混合专家（MoE）架构中的新型深度学习框架。基于随机微分方程的理论框架，MoFE将加密货币波动性概念化为多频率分量的叠加，包括基于用户网络的基本面增长、挖矿成本和减半机制导致的季节性波动，以及市场情绪引发的混乱。具体而言，专门的自适应傅里叶神经算子（AFNO）和卷积双域专家学习连续的函数到函数映射，以封装全局频谱趋势、周期性调整和微观结构，而基于动态门控的MoE机制能够在不同市场制度间实现自适应策略切换。对2020年1月至2025年12月期间比特币数据集的大量实验表明，MoFE在T+1和T+5预测 horizon 中均实现了最先进（SOTA）的性能。值得注意的是，该模型有效缓解了相位滞后效应，提供了更优的方向准确率（DA）和信息系数（IC）。在高保真模拟交易环境中，这些预测优势转化为显著的超额收益和稳健的风险调整后表现，特征为高夏普比率。
英文摘要
Forecasting cryptocurrency prices remains a formidable challenge due to inherent non-stationarity, abrupt regime shifts, and multi-scale stochastic dependencies. Conventional deep learning models often struggle to capture complex underlying dynamics, frequently resulting in persistent phase-lagged predictions. To address these limitations, we propose MoFE, a novel deep learning framework that integrates Fourier Neural Operators (FNOs) within a Mixture-of-Experts (MoE) architecture. Rooted in the theoretical framework of stochastic differential equations, MoFE conceptualizes cryptocurrency volatility as a superposition of multi-frequency components, which includes user network based fundamental growth, mining costs and halving mechanism caused seasonal volatility, and market sentiment-induced chaos. Specifically, specialized adaptive FNO (AFNO) and Convolution dual-domain experts learn continuous function-to-function mappings to encapsulate global spectral trends, cyclical adjustments and microstructures, while a dynamic gating based MoE mechanism enables adaptive strategy switching across diverse market regimes. Extensive experiments on Bitcoin datasets spanning January 2020 to December 2025 demonstrate that MoFE achieves state-of-the-art (SOTA) performance in both T+1 and T+5 forecasting horizons. Notably, the model effectively mitigates the phase-lag effect, delivering superior Directional Accuracy (DA) and Information Coefficient (IC). In high-fidelity simulated trading environments, these predictive gains transfer into significant excess returns and robust risk-adjusted performance, characterized by a high Sharpe ratio.
Comments9 pages, 7 figures. Published in 2026 IEEE International Conference on Blockchain and Cryptocurrency (ICBC)
Journal ref2026 IEEE International Conference on Blockchain and Cryptocurrency (ICBC), 2026, pp. 1-9
DOI：10.1109/ICBC67748.2026.11575439
