{
  "title": "UnFEAR: Unsupervised Feature Extraction Clustering with an Application to Crisis Regimes Classification",
  "publication": "IMF Working Papers, November 25, 2020",
  "sourceUrl": "https://www.imf.org/en/publications/wp/issues/2020/11/25/unfear-unsupervised-feature-extraction-clustering-with-an-application-to-crisis-regimes-49870",
  "canonical": "https://www.imf.org/en/publications/wp/issues/2020/11/25/unfear-unsupervised-feature-extraction-clustering-with-an-application-to-crisis-regimes-49870",
  "overlayPath": "/en/publications/wp/issues/2020/11/25/unfear-unsupervised-feature-extraction-clustering-with-an-application-to-crisis-regimes-49870/index.md",
  "summary": "We introduce unFEAR, Unsupervised Feature Extraction Clustering, to identify economic crisis regimes. Given labeled crisis and non-crisis episodes and the corresponding features values, unFEAR uses unsupervised representation learning and a novel mode contrastive autoencoder to group episodes into t",
  "sections": [
    {
      "heading": "Summary",
      "content": "- Introduces unFEAR, Unsupervised Feature Extraction Clustering, to identify economic crisis regimes.\n- Given labeled crisis and non-crisis episodes and the corresponding features values, unFEAR uses unsupervised representation learning and a novel mode contrastive autoencoder to group episodes into time-invariant non-overlapping clusters, each of which could be identified with a different regime.\n- The likelihood that a country may experience an econmic crisis could be set equal to its cluster crisis frequency.\n- unFEAR could serve as a first step towards developing cluster-specific crisis prediction models tailored to each crisis regime."
    },
    {
      "heading": "Methodology and Technical Features",
      "content": "- Unsupervised representation learning is used to extract features from crisis and non-crisis episodes.\n- A novel mode contrastive autoencoder is central to grouping episodes into time-invariant non-overlapping clusters.\n- Clustering output: non-overlapping clusters that can be associated with distinct crisis regimes.\n- Uses labeled crisis and non-crisis episodes and their corresponding features values as input."
    },
    {
      "heading": "Applications and Implications for Crisis Prediction",
      "content": "- Cluster crisis frequency can be used to set the likelihood that a country may experience an economic crisis.\n- Enables development of cluster-specific crisis prediction models tailored to each crisis regime.\n- Addresses the biased label problem via unsupervised feature extraction and clustering."
    },
    {
      "heading": "Subject Areas and Keywords",
      "content": "- Subject: Early warning systems, Economic and financial statistics, Financial crises, Financial statistics, Machine learning, Technology\n- Keywords: autoencoder, biased label problem, clustering, crisis data points, crisis frequency, crisis observation, crisis prediction, crisis risk, deep learning, Early warning systems, Global, machine learning, unsupervised feature extraction, WP"
    },
    {
      "heading": "Publication and Metadata",
      "content": "- Pages: 24\n- Volume: 2020\n- DOI: https://doi.org/10.5089/9781513561660.001\n- Issue: 262\n- Series: Working Paper No. 2020/262\n- Stock No: WPIEA2020262\n- ISBN: 9781513561660\n- ISSN: 1018-5941\n- Author: Jorge A Chan-Lau\n- Publication date: November 25, 2020\n- Series title: IMF Working Papers\n\nSource: UnFEAR: Unsupervised Feature Extraction Clustering with an Application to Crisis Regimes Classification, IMF Working Papers (Working Paper No. 2020/262).\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/2020/11/25/unfear-unsupervised-feature-extraction-clustering-with-an-application-to-crisis-regimes-49870"
    }
  ],
  "bullets": [
    "[Markdown version](/en/publications/wp/issues/2020/11/25/unfear-unsupervised-feature-extraction-clustering-with-an-application-to-crisis-regimes-49870/index.md)",
    "[Structured JSON version](/en/publications/wp/issues/2020/11/25/unfear-unsupervised-feature-extraction-clustering-with-an-application-to-crisis-regimes-49870/index.json)",
    "[Bundle manifest](/en/publications/wp/issues/2020/11/25/unfear-unsupervised-feature-extraction-clustering-with-an-application-to-crisis-regimes-49870/bundle-manifest.json)",
    "Authors: Jorge A Chan-Lau",
    "Published: November 25, 2020",
    "Series: IMF Working Papers",
    "DOI: https://doi.org/10.5089/9781513561660.001",
    "Introduces unFEAR, Unsupervised Feature Extraction Clustering, to identify economic crisis regimes.",
    "Given labeled crisis and non-crisis episodes and the corresponding features values, unFEAR uses unsupervised representation learning and a novel mode contrastive autoencoder to group episodes into time-invariant non-overlapping clusters, each of which could be identified with a different regime.",
    "The likelihood that a country may experience an econmic crisis could be set equal to its cluster crisis frequency.",
    "unFEAR could serve as a first step towards developing cluster-specific crisis prediction models tailored to each crisis regime.",
    "Unsupervised representation learning is used to extract features from crisis and non-crisis episodes.",
    "A novel mode contrastive autoencoder is central to grouping episodes into time-invariant non-overlapping clusters.",
    "Clustering output: non-overlapping clusters that can be associated with distinct crisis regimes.",
    "Uses labeled crisis and non-crisis episodes and their corresponding features values as input.",
    "Cluster crisis frequency can be used to set the likelihood that a country may experience an economic crisis.",
    "Enables development of cluster-specific crisis prediction models tailored to each crisis regime.",
    "Addresses the biased label problem via unsupervised feature extraction and clustering.",
    "Subject: Early warning systems, Economic and financial statistics, Financial crises, Financial statistics, Machine learning, Technology",
    "Keywords: autoencoder, biased label problem, clustering, crisis data points, crisis frequency, crisis observation, crisis prediction, crisis risk, deep learning, Early warning systems, Global, machine learning, unsupervised feature extraction, WP",
    "Pages: 24",
    "Volume: 2020",
    "DOI: https://doi.org/10.5089/9781513561660.001",
    "Issue: 262",
    "Series: Working Paper No. 2020/262",
    "Stock No: WPIEA2020262",
    "ISBN: 9781513561660",
    "ISSN: 1018-5941",
    "Author: Jorge A Chan-Lau",
    "Publication date: November 25, 2020",
    "Series title: IMF Working Papers",
    "**Working Paper**"
  ],
  "related": [
    {
      "title": "Working Paper",
      "role": "paper",
      "sourceUrl": "https://www.imf.org/-/media/files/publications/wp/2020/english/wpiea2020262-print-pdf.pdf",
      "summary": {
        "path": "/-/media/files/publications/wp/2020/english/wpiea2020262-print-pdf.pdf.md",
        "mime": "text/markdown"
      },
      "binary": {
        "path": "/-/media/files/publications/wp/2020/english/wpiea2020262-print-pdf.pdf",
        "mime": "application/pdf"
      }
    }
  ],
  "alternates": {
    "markdown": "/en/publications/wp/issues/2020/11/25/unfear-unsupervised-feature-extraction-clustering-with-an-application-to-crisis-regimes-49870/index.md",
    "json": "/en/publications/wp/issues/2020/11/25/unfear-unsupervised-feature-extraction-clustering-with-an-application-to-crisis-regimes-49870/index.json",
    "bundleManifest": "/en/publications/wp/issues/2020/11/25/unfear-unsupervised-feature-extraction-clustering-with-an-application-to-crisis-regimes-49870/bundle-manifest.json"
  },
  "generatedAtUtc": "2026-09-16T18:35:04.833Z"
}