{
  "fetched_at": "2026-10-20T02:20:07Z",
  "source_url": "https://www.kaggle.com/competitions/fair-classification/data",
  "pages": [
    {
      "name": "rules",
      "content": "- Each group should form a team.\n- Please name your team by uni separated by \"_\". For example, if a groups consists of three students with uni \"aa1234\", \"bb1234\" and \"cc1234\", you should name your team as \"aa1234_bb1234_cc1234\".\n- Your team can submit at most two submissions per day.\n- You are free to use any publicly available resources for this challenge as long as you cite them.\n- You are encouraged to discuss with but <strong>is not</strong> allowed to copy predictions from another team.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - the training set</li>\n<li><strong>test.csv</strong> - the testing set</li>\n<li><strong>test_sample1.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n\n<h2>Predicted Label</h2>\n<strong>income:</strong> >50K$ (corresponds to 1 in the income field), <=50K$ (corresponds to 0 in the income field).\n\n<h2>Data fields</h2>\n<ul>\n<li><strong>age</strong>: continuous.</li>\n<li><strong>workclass</strong>: Private, Self-emp-not-inc, Self-emp-inc, Federal-gov, Local-gov, State-gov, Without-pay, Never-worked.</li>\n<li><strong>fnlwgt</strong>: continuous. It represents the number of units in the target population that the responding unit represents.</li>\n<li><strong>education</strong>: Bachelors, Some-college, 11th, HS-grad, Prof-school, Assoc-acdm, Assoc-voc, 9th, 7th-8th, 12th, Masters, 1st-4th, 10th, Doctorate, 5th-6th, Preschool.</li>\n<li><strong>education-num</strong>: continuous.</li>\n<li><strong>marital-status</strong>: Married-civ-spouse, Divorced, Never-married, Separated, Widowed, Married-spouse-absent, Married-AF-spouse.</li>\n<li><strong>occupation</strong>: Tech-support, Craft-repair, Other-service, Sales, Exec-managerial, Prof-specialty, Handlers-cleaners, Machine-op-inspct, Adm-clerical, Farming-fishing, Transport-moving, Priv-house-serv, Protective-serv, Armed-Forces.\n<li><strong>relationship</strong>: Wife, Own-child, Husband, Not-in-family, Other-relative, Unmarried.</li>\n<li><strong>race</strong>: 0, 1.</li>\n<li><strong>gender(sensitive arribute)</strong>: 0, 1.</li>\n<li><strong>capital-gain</strong>: continuous.</li>\n<li><strong>capital-loss</strong>: continuous.</li>\n<li><strong>hours-per-week</strong>: continuous. An individual's working hours per week</li>\n<li><strong>native-country</strong>: United-States, Cambodia, England, Puerto-Rico, Canada, Germany, Outlying-US(Guam-USVI-etc), India, Japan, Greece, South, China, Cuba, Iran, Honduras, Philippines, Italy, Poland, Jamaica, Vietnam, Mexico, Portugal, Ireland, France, Dominican-Republic, Laos, Ecuador, Taiwan, Haiti, Columbia, Hungary, Guatemala, Nicaragua, Scotland, Thailand, Yugoslavia, El-Salvador, Trinadad&Tobago, Peru, Hong, Holand-Netherlands.</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p> \nImagine you are an expert hired to make prediction on one's income. Given some information about a person, your task is to predict if the person's annual income level is greater than 50K$ or not. The task, however, is not as simple as you thought initially. Rather than purely maximizing prediction accuracy, your employer has an extra requirement on the fairness of your predictions. Specifically, your prediction must follow a relaxed version of demographic parity for the binary sensitive attribute \"gender\". For details, check out the <strong> Evaluation </strong> section\n</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<h2>Notations</h2>\n<p>\\[\nA =\\text{gender}, \\hat{Y}=\\text{prediction on the income level}, Y=\\text{ground-truth income level}.\n\\]</p>\n<h2>Final Score</h2>\n<p>\\[\nAccuracy := \\mathbb{P} [\\hat{Y}=Y] \n\\]</p>\n<p>\\[ DDP := \\vert \\mathbb{P}[\\hat{Y}=1|A=0] - \\mathbb{P}[\\hat{Y}=1|A=1]\\vert\n\\]</p>\n<p>\\[ Th := 0.1\n\\]</p>\n<p>\\[\n\\text{ If } DDP &gt; Th, Bias :=  7^{DDP-Th} - 1,  \\text{ else, } Bias := 0.\n\\] </p>\n<p>\\[ Score := Accuracy - Bias  \\]</p>\n<p> The leaderboard will only show your prediction's Accuracy on 50% randomly selected testing points. Your final score will be estimated offline after the submission is closed.</p>\n<h2>Submission Format</h2>\n<p>Submission files should contain two columns: id and income. id should go from 0 to 8996. income should be your prediction on an individual's income level (i.e. 0 or 1). </p>\nFor an illustration, please check out <strong>test_sample1.csv</strong> in the <strong>Data</strong> section.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}