{
  "fetched_at": "2026-10-20T04:55:24Z",
  "source_url": "https://www.kaggle.com/competitions/data-analytics-challenge-prodigy18/data",
  "pages": [
    {
      "name": "rules",
      "content": "\n\n<p>\nJudging Criteria:\nAccuracy<br>\nPercentage improvement in accuracy<br>\nImprovement and simplicity of code<br>\nKnowledge of statistical operations<br>\nData Modelling<br>\nFamiliarity with different methods to improve accuracy Rules: -<br>\nTeam size are not fixed but must not exceed 2.<br>\nEach team member must present a minimum of 1 slide in front of judges<br>\nPeople from different colleges are not allowed to make teams.<br>\nThey are not allowed to resource other than those provide by event organizers.<br>\nAny sort of plagiarism if found will lead to direct disqualification.<br>\nIn case of any dispute, the decision taken by event organizer shall be final and abiding.<br>\nThe code file by participants should also be submitted by participants which will separately ran by events team member to ensure removal of any malpractices.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p>Following Section Contains data to be used for Data Analytics challenge for Prodigy'18. There are 3 files down here.\n\n - Prodigy'18 Train data -  This is a CSV file (.csv) which participants need to use to build and train there model on. \n - Prodigy'18 Test data -  This is a CSV file (.csv) which participants need to use to do prediction on. \n\n<p>A company has an internal policy of giving promotion to it's candidate through very long process. But this whole process is very time consuming and tedious. Given data in training and test set consists of info related to each individual who went through the whole process of promotion. Now, using test data participants need to predict whether or not corresponding individual is gettign promoted.\n\n<h2>File descriptions</h2>\n<ul>\n<li><strong> Prodigy'18 Train data </strong> -  This is a CSV file (.csv) which participants need to use to build and train there model on, the training set</li>\n<li><strong> Prodigy'18 Test data </strong> -  This is a CSV file (.csv) which participants need to use to do prediction on, the test set</li>\n<li><strong>Prodigy'18 Sample Submission File</strong> - a sample submission file in the correct format</li>\n\n<h2>Data fields</h2>\n<ul>\n<li><strong>is_promoted</strong>Indicator of whether employee got promoted or not and the final target value</li>\nRest of the fields are self explanatory\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "About The Event",
      "content": "<p>\nThis event caters the needs of all those who find data interesting, amusing and excel in telling stories using data and can show the world the power of data! Data is now a very crucial part of any business and research and most of them heavily depends upon finding patterns in data. This event will aim on making people aware of finding and predicting searching results using data and hence helping various business excelling in real life problems given to them.</p>\n\nFormat:\n- Participants will be given data in form of .csv format.<br>\n- Allowed platforms for coding are R (using R studio), Python (using Spyder or Jupyter Notebook) and Excel.<br>\n- Competition will be hosted online through Kaggle.<br>\n- Participated are supposed to do exploratory analysis on code.<br>\n- Task will be divided into Data Pre-processing, Data Training, Data Prediction<br>\n- Participants are allowed to submit their entry for maximum of 20 times max.<br>\n- Participants overall improvement of accuracy along with final accuracy, complexity of model used.<br>\n- Plagiarism of any form if found will lead to direct disqualification of team.<br>\n- Final submission will be taken in form of .csv file where participants have to submit their predictions of respective id(s) and detailed explanation of approached used by them<br>\n\nFee :\nNIL<br>\nPrize Money :\n7500 total",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "\n<hr />\n<p>The evaluation metric for this competition is  AUC Score. Find more about <a href=\"https://developers.google.com/machine-learning/crash-course/classification/roc-and-auc\"> AUC Score </a> over here.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}