mlsanityData to 7 Oct 2026

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

arXiv 2511.07014 ↗First posted 10 Nov 2025cs.CE cs.AI econ.EMcited by 1

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 19 of its 52 references that are in the map. First posted on arXiv 10 Nov 2025.

Builds on

19 of 52 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024A Financial Time Series Denoiser Based on Diffusion Model2 Sep
  2. 2024MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process9 Mar
  3. 2024Diffusion-TS: Interpretable Diffusion for General Time Series Generation4 Mar
  4. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting21 Jul
  5. 2022Flow Matching for Generative Modeling6 Oct
  6. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation7 Jul
  7. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting28 Jan

Other references · 12

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2016Layer Normalizationcited by 5,579
  6. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  7. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  8. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 315
  9. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
  10. 2019Quant GANs: Deep Generation of Financial Time Seriescited by 107
  11. 2019Deep Learning in Asset Pricingcited by 41
  12. 2020Conditional Sig-Wasserstein GANs for Time Series Generationcited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Beyond Linear Dynamics: Neural Bilinear Dynamical Models for Time Series Forecastingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024DiffSTOCK: Probabilistic relational Stock Market Predictions using Diffusion Models
  2. 2024DiffsFormer: A Diffusion Transformer on Stock Factor Augmentation
  3. 2025Diffusion Factor Models: Generating High-Dimensional Returns with Factor Structure
  4. 2025Factor-Based Conditional Diffusion Model for Contextual Portfolio Optimization
  5. 2026Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios
  6. 2026GARDiff: Graph-Aligned Residual Diffusion for Probabilistic Multivariate Time-Series Forecasting
  7. 2026Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting
  8. 2026DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting