{
  "title": "Nowcasting GDP - A Scalable Approach Using DFM, Machine Learning and Novel Data, Applied to European Economies",
  "publication": "IMF Working Papers, March 11, 2022",
  "sourceUrl": "https://www.imf.org/en/publications/wp/issues/2022/03/11/nowcasting-gdp-a-scalable-approach-using-dfm-machine-learning-and-novel-data-applied-to-513703",
  "canonical": "https://www.imf.org/en/publications/wp/issues/2022/03/11/nowcasting-gdp-a-scalable-approach-using-dfm-machine-learning-and-novel-data-applied-to-513703",
  "overlayPath": "/en/publications/wp/issues/2022/03/11/nowcasting-gdp-a-scalable-approach-using-dfm-machine-learning-and-novel-data-applied-to-513703/index.md",
  "summary": "This paper describes recent work to strengthen nowcasting capacity at the IMF’s European department. It motivates and compiles datasets of standard and nontraditional variables, such as Google search and air quality.",
  "sections": [
    {
      "heading": "Summary and purpose",
      "content": "- Describes recent work to strengthen nowcasting capacity at the IMF’s European department.\n- Motivates and compiles datasets of standard and nontraditional variables, such as Google search and air quality.\n- Applies standard dynamic factor models (DFMs) and several machine learning (ML) algorithms to nowcast GDP growth across a heterogeneous group of European economies during normal and crisis times.\n- Conclusion: Most methods significantly outperform the AR(1) benchmark model.\n- Conclusion: DFMs tend to perform better during normal times.\n- Conclusion: Many of the ML methods used performed strongly at identifying turning points.\n- Claim: The approach is easily applicable to other countries, subject to data availability."
    },
    {
      "heading": "Data and inputs",
      "content": "- Datasets include standard and nontraditional variables, explicitly mentioning Google search and air quality.\n- Focus on large and varied data inputs suitable for factor models and machine learning algorithms."
    },
    {
      "heading": "Methods and modeling approach",
      "content": "- Standard dynamic factor models (DFMs) are a primary modeling framework.\n- Several machine learning (ML) algorithms are applied alongside DFMs.\n- Benchmark comparison against an AR(1) model."
    },
    {
      "heading": "Key findings and performance",
      "content": "- Most methods significantly outperform the AR(1) benchmark model.\n- DFMs perform relatively better in normal (non-crisis) periods.\n- Many ML methods perform strongly at identifying turning points in GDP growth.\n- The framework is scalable and intended for application across a heterogeneous group of European economies."
    },
    {
      "heading": "Applicability and limitations",
      "content": "- Approach is easily applicable to other countries, subject to data availability.\n- Explicit focus on both normal and crisis times, highlighting differential strengths of DFMs and ML methods.\n\n---\n\n Content in this bundle\n\n- Working Paper\n  - Working Paper (Markdown version){rel=\"alternate\" type=\"text/markdown\"}\n  - Working Paper (PDF){rel=\"external\" type=\"application/pdf\"}\n\n---\n\nSource: https://www.imf.org/en/publications/wp/issues/2022/03/11/nowcasting-gdp-a-scalable-approach-using-dfm-machine-learning-and-novel-data-applied-to-513703"
    }
  ],
  "bullets": [
    "[Markdown version](/en/publications/wp/issues/2022/03/11/nowcasting-gdp-a-scalable-approach-using-dfm-machine-learning-and-novel-data-applied-to-513703/index.md)",
    "[Structured JSON version](/en/publications/wp/issues/2022/03/11/nowcasting-gdp-a-scalable-approach-using-dfm-machine-learning-and-novel-data-applied-to-513703/index.json)",
    "[Bundle manifest](/en/publications/wp/issues/2022/03/11/nowcasting-gdp-a-scalable-approach-using-dfm-machine-learning-and-novel-data-applied-to-513703/bundle-manifest.json)",
    "Authors: Jean-Francois Dauphin, Kamil Dybczak, Morgan Maneely, Marzie Taheri Sanjani, Nujin Suphaphiphat, Yifei Wang, Hanqi Zhang",
    "Published: March 11, 2022",
    "Series: IMF Working Papers",
    "DOI: https://doi.org/10.5089/9798400204425.001",
    "Describes recent work to strengthen nowcasting capacity at the IMF’s European department.",
    "Motivates and compiles datasets of standard and nontraditional variables, such as Google search and air quality.",
    "Applies standard dynamic factor models (DFMs) and several machine learning (ML) algorithms to nowcast GDP growth across a heterogeneous group of European economies during normal and crisis times.",
    "Conclusion: Most methods significantly outperform the AR(1) benchmark model.",
    "Conclusion: DFMs tend to perform better during normal times.",
    "Conclusion: Many of the ML methods used performed strongly at identifying turning points.",
    "Claim: The approach is easily applicable to other countries, subject to data availability.",
    "Datasets include standard and nontraditional variables, explicitly mentioning Google search and air quality.",
    "Focus on large and varied data inputs suitable for factor models and machine learning algorithms.",
    "Standard dynamic factor models (DFMs) are a primary modeling framework.",
    "Several machine learning (ML) algorithms are applied alongside DFMs.",
    "Benchmark comparison against an AR(1) model.",
    "Most methods significantly outperform the AR(1) benchmark model.",
    "DFMs perform relatively better in normal (non-crisis) periods.",
    "Many ML methods perform strongly at identifying turning points in GDP growth.",
    "The framework is scalable and intended for application across a heterogeneous group of European economies.",
    "Approach is easily applicable to other countries, subject to data availability.",
    "Explicit focus on both normal and crisis times, highlighting differential strengths of DFMs and ML methods.",
    "**Working Paper**"
  ],
  "related": [
    {
      "title": "Working Paper",
      "role": "paper",
      "sourceUrl": "https://www.imf.org/-/media/files/publications/wp/2022/english/wpiea2022052-print-pdf.pdf",
      "summary": {
        "path": "/-/media/files/publications/wp/2022/english/wpiea2022052-print-pdf.pdf.md",
        "mime": "text/markdown"
      },
      "binary": {
        "path": "/-/media/files/publications/wp/2022/english/wpiea2022052-print-pdf.pdf",
        "mime": "application/pdf"
      }
    }
  ],
  "alternates": {
    "markdown": "/en/publications/wp/issues/2022/03/11/nowcasting-gdp-a-scalable-approach-using-dfm-machine-learning-and-novel-data-applied-to-513703/index.md",
    "json": "/en/publications/wp/issues/2022/03/11/nowcasting-gdp-a-scalable-approach-using-dfm-machine-learning-and-novel-data-applied-to-513703/index.json",
    "bundleManifest": "/en/publications/wp/issues/2022/03/11/nowcasting-gdp-a-scalable-approach-using-dfm-machine-learning-and-novel-data-applied-to-513703/bundle-manifest.json"
  },
  "generatedAtUtc": "2026-09-16T20:53:00.181Z"
}