{
  "abstract": "Credit-card fraud detection is difficult because fraudulent transactions represent a very small\n\nshare of observed payments, while false negatives and false positives impose different\n\noperational costs. This study presents a reproducible framework for evaluating fraud-detection\n\nclassifiers under extreme class imbalance, with explicit controls for data leakage, threshold\n\nselection, and decision cost. The protocol covers dataset validation, partition design,\n\ntraining-only preprocessing and resampling, baseline models, validation-based threshold\n\nselection, and reporting of ranking, classification, calibration, and workload measures. It\n\nprioritizes average precision, precision, recall, false-positive rate, confusion counts, and alert\n\nvolume rather than accuracy alone.\n\nThe public European Credit Card Fraud Detection benchmark is described as containing\n\n284,807 transactions, including 492 fraud cases, for a fraud prevalence of approximately\n\n0.1727%. From these published aggregate counts, an all-legitimate rule achieves\n\napproximately 99.8273% accuracy while detecting no fraud. This analytical baseline\n\ndemonstrates why accuracy alone is inadequate. The transaction-level CSV was not available\n\nin the execution environment used for this study; consequently, no trained-model comparison\n\nor model-specific performance claim is presented. The contribution is a transparent evaluation\n\ndesign and a verified calculation from published aggregate counts, not a ranking of fitted\n\nclassifiers. The paper also examines temporal validity, anonymized features, privacy, fairness,\n\ncalibration, and the boundary between benchmark results and production readiness.\n\nKeywords: Credit-card fraud detection; extreme class imbalance; data leakage; cost-sensitive\n\nevaluation; decision thresholds; precision–recall analysis.",
  "abstract_shown": true,
  "affiliations": [
    "IIMT College of Engineering, Greater Noida, Dr. A.P.J. Abdul Kalam Technical University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Rayhan Khan"
    },
    {
      "affs": [
        0
      ],
      "name": "Reena Baghel"
    },
    {
      "affs": [
        0
      ],
      "name": "Reva Sharma"
    },
    {
      "affs": [
        0
      ],
      "name": "Roshni Singh"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/b404wk6b45zts.bib",
  "cited_by": 0,
  "doi": "10.5281/zenodo.23448825",
  "fulltext_url": null,
  "id": "b404wk6b45zts",
  "issns": [],
  "landing_url": "https://zenodo.org/records/23448825",
  "language": "eng",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://zenodo.org/api/records/23448825/files/Credit_Card_Fraud_Research_Paper_FINAL_FINAL_20_Pages-1.pdf/content",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-18",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/b404wk6b45zts.ris",
  "sources": [
    {
      "first_seen": "2026-11-01T12:21:16Z",
      "native_id": "23448825",
      "source": "zenodo",
      "url": "https://zenodo.org/records/23448825"
    }
  ],
  "subjects": [],
  "title": "Cost-Sensitive and Leakage-Aware Evaluation of Credit Card Fraud Detection Under Extreme Class Imbalance",
  "title_text": "Cost-Sensitive and Leakage-Aware Evaluation of Credit Card Fraud Detection Under Extreme Class Imbalance",
  "type": "preprint",
  "updated_at": "2026-11-01T12:21:16Z",
  "url": "https://research.draconitic.com/paper/b404wk6b45zts",
  "venue": "Zenodo",
  "versions": []
}