{
  "title": "Deus ex Machina? A Framework for Macro Forecasting with Machine Learning",
  "publication": "IMF Working Papers, February 28, 2020",
  "sourceUrl": "https://www.imf.org/en/publications/wp/issues/2020/02/28/deus-ex-machina-a-framework-for-macro-forecasting-with-machine-learning-49094",
  "canonical": "https://www.imf.org/en/publications/wp/issues/2020/02/28/deus-ex-machina-a-framework-for-macro-forecasting-with-machine-learning-49094",
  "overlayPath": "/en/publications/wp/issues/2020/02/28/deus-ex-machina-a-framework-for-macro-forecasting-with-machine-learning-49094/index.md",
  "summary": "We develop a framework to nowcast (and forecast) economic variables with machine learning techniques. We explain how machine learning methods can address common shortcomings of traditional OLS-based models and use several machine learning models to predict real output growth with lower forecast erro",
  "sections": [
    {
      "heading": "Framework and methodology",
      "content": "- Develops a framework to nowcast (and forecast) economic variables with machine learning techniques.\n- Explains how machine learning methods can address common shortcomings of traditional OLS-based models.\n- Uses several machine learning models to predict real output growth.\n- Combines multiple machine learning models into ensembles to further reduce forecast errors.\n- Identifies measures of variable importance to help improve the transparency of machine learning-based forecasts.\n- Keywords and methodological terms used: Cross-validation, Ensemble, Factor models, Random Forest, RF algorithm, SVM regression, ML model, ML method, Nowcasting."
    },
    {
      "heading": "Main findings and empirical results",
      "content": "- Machine learning models predict real output growth with lower forecast errors than traditional OLS-based models.\n- Combining multiple machine learning models into ensembles lowers forecast errors even further.\n- Applying the framework to Turkey reduces forecast errors by at least 30 percent relative to traditional models.\n- The framework better predicts economic volatility compared with traditional models.\n- Implication: Machine learning techniques could be an important part of the macro forecasting toolkit of many countries."
    },
    {
      "heading": "Policy implications and recommendations",
      "content": "- Incorporate machine learning techniques into macro forecasting toolkits to improve forecast accuracy and volatility prediction.\n- Use ensembles of diverse machine learning models to achieve further reductions in forecast error.\n- Employ measures of variable importance to increase transparency and interpretability of machine learning-based forecasts.\n- Address common shortcomings of OLS-based models by leveraging machine learning methods and cross-validation practices."
    },
    {
      "heading": "Publication and metadata",
      "content": "- Authors: Marijn A. Bolhuis, Brett Rayner\n- Publication date: February 28, 2020\n- Series: Working Paper No. 2020/045\n- Issue: 045\n- Volume: 2020\n- Pages: 25\n- DOI: https://doi.org/10.5089/9781513531724.001\n- ISBN: 9781513531724\n- ISSN: 1018-5941\n- Stock No: WPIEA2020045\n\nIMF Working Papers — Deus ex Machina? A Framework for Macro Forecasting with Machine Learning (Marijn A. Bolhuis; Brett Rayner), February 28, 2020.\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/2020/02/28/deus-ex-machina-a-framework-for-macro-forecasting-with-machine-learning-49094"
    }
  ],
  "bullets": [
    "[Markdown version](/en/publications/wp/issues/2020/02/28/deus-ex-machina-a-framework-for-macro-forecasting-with-machine-learning-49094/index.md)",
    "[Structured JSON version](/en/publications/wp/issues/2020/02/28/deus-ex-machina-a-framework-for-macro-forecasting-with-machine-learning-49094/index.json)",
    "[Bundle manifest](/en/publications/wp/issues/2020/02/28/deus-ex-machina-a-framework-for-macro-forecasting-with-machine-learning-49094/bundle-manifest.json)",
    "Authors: Marijn A. Bolhuis, Brett Rayner",
    "Published: February 28, 2020",
    "Series: IMF Working Papers",
    "DOI: https://doi.org/10.5089/9781513531724.001",
    "Develops a framework to nowcast (and forecast) economic variables with machine learning techniques.",
    "Explains how machine learning methods can address common shortcomings of traditional OLS-based models.",
    "Uses several machine learning models to predict real output growth.",
    "Combines multiple machine learning models into ensembles to further reduce forecast errors.",
    "Identifies measures of variable importance to help improve the transparency of machine learning-based forecasts.",
    "Keywords and methodological terms used: Cross-validation, Ensemble, Factor models, Random Forest, RF algorithm, SVM regression, ML model, ML method, Nowcasting.",
    "Machine learning models predict real output growth with lower forecast errors than traditional OLS-based models.",
    "Combining multiple machine learning models into ensembles lowers forecast errors even further.",
    "Applying the framework to Turkey reduces forecast errors by at least 30 percent relative to traditional models.",
    "The framework better predicts economic volatility compared with traditional models.",
    "Implication: Machine learning techniques could be an important part of the macro forecasting toolkit of many countries.",
    "Incorporate machine learning techniques into macro forecasting toolkits to improve forecast accuracy and volatility prediction.",
    "Use ensembles of diverse machine learning models to achieve further reductions in forecast error.",
    "Employ measures of variable importance to increase transparency and interpretability of machine learning-based forecasts.",
    "Address common shortcomings of OLS-based models by leveraging machine learning methods and cross-validation practices.",
    "Authors: Marijn A. Bolhuis, Brett Rayner",
    "Publication date: February 28, 2020",
    "Series: Working Paper No. 2020/045",
    "Issue: 045",
    "Volume: 2020",
    "Pages: 25",
    "DOI: https://doi.org/10.5089/9781513531724.001",
    "ISBN: 9781513531724",
    "ISSN: 1018-5941",
    "Stock No: WPIEA2020045",
    "**Working Paper**"
  ],
  "related": [
    {
      "title": "Working Paper",
      "role": "paper",
      "sourceUrl": "https://www.imf.org/-/media/files/publications/wp/2020/english/wpiea2020045-print-pdf.pdf",
      "summary": {
        "path": "/-/media/files/publications/wp/2020/english/wpiea2020045-print-pdf.pdf.md",
        "mime": "text/markdown"
      },
      "binary": {
        "path": "/-/media/files/publications/wp/2020/english/wpiea2020045-print-pdf.pdf",
        "mime": "application/pdf"
      }
    }
  ],
  "alternates": {
    "markdown": "/en/publications/wp/issues/2020/02/28/deus-ex-machina-a-framework-for-macro-forecasting-with-machine-learning-49094/index.md",
    "json": "/en/publications/wp/issues/2020/02/28/deus-ex-machina-a-framework-for-macro-forecasting-with-machine-learning-49094/index.json",
    "bundleManifest": "/en/publications/wp/issues/2020/02/28/deus-ex-machina-a-framework-for-macro-forecasting-with-machine-learning-49094/bundle-manifest.json"
  },
  "generatedAtUtc": "2026-09-18T16:44:19.101Z"
}