{
  "fetched_at": "2026-10-19T15:51:00Z",
  "source_url": "https://www.kaggle.com/competitions/dota-2-simplified-cs-677-o-2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "File descriptions\n\ntrain_data.csv: basic training set\n\ntest_data.csv: basic test set\n\n\nData fields\n\nPlayer’s stats (start with a prefix to identify a player: ‘r’ for Radiant team or ‘d’ for Dire team and a player’s number) include the following fields:\n\nhero_id\n\nK/D/A: kills, deaths and assists\n\nlh - last hits - number of enemy team creeps killed\n\ndenies - number of same-team creeps killed to deny enemy gold\n\ngold\n\nxp\n\nlevel\n\nhealth and max_health\n\nmax_mana\n\nx, y - current location of a player\n\nstuns\n\ncreeps_stacked\n\ncamps_stacked\n\nrune_pickups\n\nfirstblood_claimed\n\nteamfight_participation\n\ntowers_killed\n\nroshans_killed\n\nobs_placed, sen_placed - the number of observer and sentry wards placed by a player\n\nThere are also time series fields that may prove useful during this competition. The field ‘times’ consists of an array of time marks and ‘_t’ fields with values for different features:\n\ngold_t - gold values for different time marks\nxp_t - experience values\nlh - last hits\ndn_t - denied creeps\n\nBe inventive and good luck!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This is Binary Classification problem",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The Metric that will be used is ROC AUC. \nMore information on ROC AUC is: https://developers.google.com/machine-learning/crash-course/classification/roc-and-auc\n\n## Submission File\nFor each ID in the test set, you must predict if radiant wins or not. The file should contain a header and have the following format:\n\n    ID, radiant_win\n    2,0\n    5,1\n    6,0\n    etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!\n\nThe Grade will be computed based on the PRIVATE leaderboard, not PUBLIC. If you overfit to PUBLIC leaderboard, your score on private leaderboard, might not be reflective of your standings.\n\nYou Must Beat Simple Baseline and Advanced Baseline to receive at least some grade. Students who don't beat Advanced Baseline will receive 0.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "## Introduction\n![](https://cdn.cloudflare.steamstatic.com/apps/dota2/images/dota2_social.jpg)\nDota 2 is the game that took by storm the world of computer gamers. In this competition we will try to predict the winner of the game based on the statistics of the first several minutes of the game\n\n## ML Problem Definition\nThis is Binary Classification Problem. The data is structured (tabular, csv data)\n\n## Credits\nThis competition is the simplified version of competitions held in:\n- Yandex Data School by Pavel Gein\n- Higher School of Economics by Konstantin Vorontsov\n- ODS.AI by Yuriy Kashnitskiy\n ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}