arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.07014cs.CEcs.AIecon.EMq-fin.PM
收藏

Diffolio:一种用于多变量概率金融时间序列预测和投资组合构建的扩散模型

Diffolio: A Diffusion Model for Multivariate Probabilistic Financial Time-Series Forecasting and Portfolio Construction

Hankuk University of Foreign Studies(韩国外国语大学);Independent Researcher(独立研究员);Korea Institute for Advanced Study(韩国高等研究院);Ajou University(亚洲大学)

So-Yoon Cho, Jin-Young Kim, Kayoung Ban, Hyeng Keun Koo, Hyun-Gyoon Kim

AI总结:

Diffolio通过层次注意力架构的去噪网络,结合相关性引导正则化,提升多变量金融时间序列预测和投资组合构建的准确性与经济意义。

摘要:

概率预测在多变量金融时间序列中对于构建考虑复杂横截面依赖关系的高效投资组合至关重要。本文提出Diffolio,一种用于多变量金融时间序列预测和投资组合构建的扩散模型。Diffolio采用具有层次注意力架构的去噪网络,包括资产层面和市场层面的层。此外,为了更好地反映横截面相关性,我们引入了一个由稳定的目标相关矩阵估计值指导的正则化器。这种结构有效地提取了历史回报、资产特定和系统性协变量中的显著特征,显著提高了预测和投资组合的性能。在12个行业投资组合的每日超额收益上的实验结果表明,Diffolio在多变量预测准确性和投资组合性能上优于各种概率预测基线。此外,在投资组合实验中,由Diffolio预测构建的投资组合表现出持续稳健的性能,从而在均值-方差切线投资组合中实现更高的夏普比率,在增长最优投资组合中实现更高的确定性等价值。这些结果证明了我们提出的Diffolio在统计准确性和经济意义方面均优于现有方法。

英文摘要:

Probabilistic forecasting is crucial in multivariate financial time-series for constructing efficient portfolios that account for complex cross-sectional dependencies. In this paper, we propose Diffolio, a diffusion model designed for multivariate financial time-series forecasting and portfolio construction. Diffolio employs a denoising network with a hierarchical attention architecture, comprising both asset-level and market-level layers. Furthermore, to better reflect cross-sectional correlations, we introduce a correlation-guided regularizer informed by a stable estimate of the target correlation matrix. This structure effectively extracts salient features not only from historical returns but also from asset-specific and systematic covariates, significantly enhancing the performance of forecasts and portfolios. Experimental results on the daily excess returns of 12 industry portfolios show that Diffolio outperforms various probabilistic forecasting baselines in multivariate forecasting accuracy and portfolio performance. Moreover, in portfolio experiments, portfolios constructed from Diffolio's forecasts show consistently robust performance, thereby outperforming those from benchmarks by achieving higher Sharpe ratios for the mean-variance tangency portfolio and higher certainty equivalents for the growth-optimal portfolio. These results demonstrate the superiority of our proposed Diffolio in terms of not only statistical accuracy but also economic significance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑