{
  "fetched_at": "2026-10-19T14:06:09Z",
  "source_url": "https://www.kaggle.com/competitions/cyprus-ai-camp-binary-classification-in-space/data",
  "pages": [
    {
      "name": "data-description",
      "content": "All the data in files.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "### Binary Classification in Space (100 points)\n\nThe score in this problem will be fractional, from 0 to 100 points.\n\n*Year 2222*. The modern cosmologist Arkadiya knows for sure that theoretically there should be a balance of *ordinary* and *dwarf* galaxies in the Universe. \nHowever, the problem of the shortage of dwarf galaxies, known since the 20th century, is that the number of observed dwarf galaxies is many times less than predicted by theory.\n\nArkadiya has a collected dataset of **1000 observed galaxies**, which are described by **13 numerical features**; the class label is known for them (0 - dwarf, 1 - ordinary).\n\nHelp Arkadiya train a **binary classifier** that will work as accurately as possible on real data — all galaxies.\n\n*P.S. The real data is a thousand times larger and confirms the theoretical distribution of ordinary and dwarf galaxies.*\n\n#### About dataset\nAll data can be downloaded [here](https://drive.google.com/drive/folders/1NAuX7-UGr-phATwB-wN4w6E74lnHBkth?usp=sharing), or from the Kaggle competition.\n\nYou are provided with three files:\n\n- The `train.csv` file contains data on 1000 observed galaxies and their classes in the target column. Each line is a set of real numbers (decimal separator is dot) separated by commas\n- The `test.csv` file contains data on unobserved galaxies that you have to label\n- The `sample_submission.csv` file is an example of a correct submission\n\n#### What should be done\nUpload the `submission.csv` file to the [Kaggle Competition](https://www.kaggle.com/competitions/cyprus-ai-camp-binary-classification-in-space), each line of which contains the class (in the `target` column) and the `Id` of the galaxy, separated by a comma.\n\nYour score on this problem will be calculated as:\n\n$$\\min(100, (\\text{accuracy} - 0.55)*294),$$\n\nwhere `accuracy` is the proportion of correctly classified galaxies, according to your predictions.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Accuracy metric.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This competition is subject to general Cyprus AI Camp rules that can be found here: https://www.kaggle.com/competitions/cyprus-ai-camp-2026-tasks/rules\n\nSpecial rules and limitations that apply for this specific task can be found in the baseline published by organizers in the `Code` section",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Binary classification.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}