{
  "abstract": "We propose a structured continuous-time stochastic volatility model for one-day-ahead integrated-variance forecasting. The model introduces a jointly evolving realized-measure state that feeds directly into latent variance dynamics, while correlated Brownian innovations capture return-linked dependence. Parameters are estimated through simulation-based predictive learning, and Monte Carlo simulation forecasts integrated variance. Across 17 equity indices, the proposed model shows strong out-of-sample performance relative to GARCH, GARCH-Itô, Realized GARCH, HAR, and HEAVY benchmarks under QLIKE, MSE, and MAE. Ablation results show that realized-measure feedback provides substantial incremental forecasting value within the proposed framework, while return-linked Brownian dependence contributes more modest complementary gains. The results support incorporating measurement-driven information directly into continuous-time latent volatility dynamics to improve integrated-variance forecasting.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.17732",
  "author_total": 3,
  "authors": [
    {
      "name": "Hongyu Yao"
    },
    {
      "name": "Zhengyang Chi"
    },
    {
      "name": "Junbin Gao"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5kd1xq8hs8pf7.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.17732",
  "fulltext_url": null,
  "id": "5kd1xq8hs8pf7",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.17732",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "q-fin.ST"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "2003|Financial Risk and Volatility Modeling"
    ]
  ],
  "openalex": "W7221795135",
  "pdf_url": "https://arxiv.org/pdf/2610.17732",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-13",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/5kd1xq8hs8pf7.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:26Z",
      "native_id": "2610.17732",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.17732"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Structured SDEs for Realized GARCH: Continuous-Time Volatility Modelling and Component-Level Analysis",
  "title_text": "Structured SDEs for Realized GARCH: Continuous-Time Volatility Modelling and Component-Level Analysis",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:26Z",
  "url": "https://research.draconitic.com/paper/5kd1xq8hs8pf7",
  "venue": "arXiv",
  "versions": []
}