{
  "title": "Forecasting Social Unrest: A Machine Learning Approach",
  "publication": "IMF Working Papers, November 5, 2021",
  "sourceUrl": "https://www.imf.org/en/publications/wp/issues/2021/11/05/forecasting-social-unrest-a-machine-learning-approach-504350",
  "canonical": "https://www.imf.org/en/publications/wp/issues/2021/11/05/forecasting-social-unrest-a-machine-learning-approach-504350",
  "overlayPath": "/en/publications/wp/issues/2021/11/05/forecasting-social-unrest-a-machine-learning-approach-504350/index.md",
  "summary": "We produce a social unrest risk index for 125 countries covering a period of 1996 to 2020. The risk of social unrest is based on the probability of unrest in the following year derived from a machine learning model drawing on over 340 indicators covering a wide range of macro-financial, socioeconomi",
  "sections": [
    {
      "heading": "Summary",
      "content": "- Produces a social unrest risk index for 125 countries covering a period of 1996 to 2020.\n- Risk is defined as the probability of unrest in the following year derived from a machine learning model.\n- The prediction model correctly forecasts unrest in the following year approximately two-thirds of the time.\n- Shapley values indicate that key drivers of the predictions include high levels of unrest, food price inflation and mobile phone penetration."
    },
    {
      "heading": "Data and Model",
      "content": "- Coverage: 125 countries.\n- Time span: 1996 to 2020.\n- Predictors: over 340 indicators covering a wide range of macro-financial, socioeconomic, development and political variables.\n- Outcome: probability of unrest in the following year as the basis for the social unrest risk index."
    },
    {
      "heading": "Model Performance and Validation",
      "content": "- Forecast accuracy: correctly forecasts unrest in the following year approximately two-thirds of the time.\n- Explainability: uses Shapley values to identify key drivers consistent with previous findings in the literature."
    },
    {
      "heading": "Key Drivers Identified",
      "content": "- High levels of prior unrest.\n- Food price inflation.\n- Mobile phone penetration.\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/2021/11/05/forecasting-social-unrest-a-machine-learning-approach-504350"
    }
  ],
  "bullets": [
    "[Markdown version](/en/publications/wp/issues/2021/11/05/forecasting-social-unrest-a-machine-learning-approach-504350/index.md)",
    "[Structured JSON version](/en/publications/wp/issues/2021/11/05/forecasting-social-unrest-a-machine-learning-approach-504350/index.json)",
    "[Bundle manifest](/en/publications/wp/issues/2021/11/05/forecasting-social-unrest-a-machine-learning-approach-504350/bundle-manifest.json)",
    "Authors: Chris Redl, Sandile Hlatshwayo",
    "Published: November 5, 2021",
    "Series: IMF Working Papers",
    "DOI: https://doi.org/10.5089/9781557758873.001",
    "Produces a social unrest risk index for 125 countries covering a period of 1996 to 2020.",
    "Risk is defined as the probability of unrest in the following year derived from a machine learning model.",
    "The prediction model correctly forecasts unrest in the following year approximately two-thirds of the time.",
    "Shapley values indicate that key drivers of the predictions include high levels of unrest, food price inflation and mobile phone penetration.",
    "Coverage: 125 countries.",
    "Time span: 1996 to 2020.",
    "Predictors: over 340 indicators covering a wide range of macro-financial, socioeconomic, development and political variables.",
    "Outcome: probability of unrest in the following year as the basis for the social unrest risk index.",
    "Forecast accuracy: correctly forecasts unrest in the following year approximately two-thirds of the time.",
    "Explainability: uses Shapley values to identify key drivers consistent with previous findings in the literature.",
    "High levels of prior unrest.",
    "Food price inflation.",
    "Mobile phone penetration.",
    "**Working Paper**"
  ],
  "related": [
    {
      "title": "Working Paper",
      "role": "paper",
      "sourceUrl": "https://www.imf.org/-/media/files/publications/wp/2021/english/wpiea2021263-print-pdf.pdf",
      "summary": {
        "path": "/-/media/files/publications/wp/2021/english/wpiea2021263-print-pdf.pdf.md",
        "mime": "text/markdown"
      },
      "binary": {
        "path": "/-/media/files/publications/wp/2021/english/wpiea2021263-print-pdf.pdf",
        "mime": "application/pdf"
      }
    }
  ],
  "alternates": {
    "markdown": "/en/publications/wp/issues/2021/11/05/forecasting-social-unrest-a-machine-learning-approach-504350/index.md",
    "json": "/en/publications/wp/issues/2021/11/05/forecasting-social-unrest-a-machine-learning-approach-504350/index.json",
    "bundleManifest": "/en/publications/wp/issues/2021/11/05/forecasting-social-unrest-a-machine-learning-approach-504350/bundle-manifest.json"
  },
  "generatedAtUtc": "2026-09-16T20:21:18.906Z"
}