{
  "id": "2203.17250",
  "version": "v1",
  "published": "2022-03-30T13:22:44.000Z",
  "updated": "2022-03-30T13:22:44.000Z",
  "title": "Generation and Simulation of Synthetic Datasets with Copulas",
  "authors": [
    "Regis Houssou",
    "Mihai-Cezar Augustin",
    "Efstratios Rappos",
    "Vivien Bonvin",
    "Stephan Robert-Nicoud"
  ],
  "categories": [
    "cs.LG",
    "cs.AI"
  ],
  "abstract": "This paper proposes a new method to generate synthetic data sets based on copula models. Our goal is to produce surrogate data resembling real data in terms of marginal and joint distributions. We present a complete and reliable algorithm for generating a synthetic data set comprising numeric or categorical variables. Applying our methodology to two datasets shows better performance compared to other methods such as SMOTE and autoencoders.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-03-30T13:22:44.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "synthetic datasets",
      "data set comprising numeric",
      "surrogate data resembling real data",
      "generate synthetic data sets",
      "simulation"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}