{
  "fetched_at": "2026-10-24T05:22:38Z",
  "source_url": "https://www.kaggle.com/competitions/eki-challenge-n1-tabular-data/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>This page shows up underneath the data files. Here you describe what files you have provided and the format of each. There is no single format for this page that is appropriate for all competitons, but you should strive to describe as much as you can here. A little time spent describing the data here can save a lot of time answering questions later.</p>\n<p>Participants should be able to answer questions like these after reading the data description: What files do I need? What should I expect the data format to be? What am I predicting? What acroynms will I encounter?</p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train_set.csv<p>The training set, with the target columns (Cover_Type)</li>\n<li><strong>test_set.csv<p>The test set, without the target columns</li>\n<li><strong>covtype.info<p>The description of the dataset as proposed by the original one</li>\n<li><strong>sample_submission.csv<p>The format to use to submit submission</li>\n</ul>\n\n<p>Original Dataset Source : https://archive.ics.uci.edu/ml/datasets/covertype</p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>This is the first monthly data challenge competition organised within Ekimetris. For this competition you will learn how to manipulate and model data from a tabular dataset, created from the open source dataset Forest Cover Type</p>\n<p>This is not only a code competition where you compete to get the best possible score on a test dataset, but also an analytics one, where you can express your creativity by building a use case around the provided data</p>\n<h2>Problematic Overview</h2>\n<p>During the past century, global warming grew as one of the most challenging problems ever faced by human kind. Many initiative have been taken so far to slow down and reverse the trend, from governmental measures like carbon taxation, to private initiative to plat some new trees.</p>\n<p>With this competition, you'll leverage a public dataset to learn to predict which kind of forest can be grown depending on several geologic informations, and build around this modelisation to create a full environnmental strategy designed to help private initiatives to optimize the effectivness of planting new trees.</p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>This competition will be evaluated according to three main axes</p>\n<hr>\n\n<h1>Excellence</h1>\n<p>This competition being evaluated on a classification task with fairly balanced classes, the metric of evaluation will be the accuracy</p>\n<p>The metric will be computed not only on your best submission (displayed on the leaderboard), but also on best score for three distinct methodologies : </p>\n<li>Standard ML : Make the most out of classical libraries like sklearn, lighgbm and xgboost</li>\n<li>AutoML : Leverage powerfull automl and stacking approaches to get the best possible score</li>\n<li>DeepLearning : Unleach the full power of deep neural network to achieve state of the art scores</li>\nIn order to be evaluated on one of these three dimension on top of the main evaluation, you will need to publish you notebook in the notebook section, and the notebook will be rerun to ensure reproducibility of your method. The name of the notebook will need to contain one of the following snippet : [StandardML], [AutoML], [DeepML]\n\n<h1>Creativity / Business Sense</h1>\n<p>The second evaluation criteria will be around your business expertise, and your ability to build and developp a convincing use case around the provided data.</p>\n<p>In order to compete on the dimension, you'll need to create a presentation support with your team and send it to the jury before the competition deadline. We will schedule a meeting for a 10-20 min restitution</p>\n\n<h1>Transmission</h1>\n<p>The goal of the competition being to learn, the last evaluation criteria will be your ability to transmit your knowledges to others</p>\n<p>To compete on this dimension, you can publish your notebook with an EDA, a methodology or a lesson, and include the snippet [Transmission] in the notebook name. The notebook with the most upvote will win</p>\n\n<h2>Submission Format</h2>\n<p><strong>For every rows in the dataset</strong>, submission files should contain two columns: id and CoverType.</p>\n<p>The file should contain a header and have the following format (same as sample_submission):</p>\n<pre>id,Cover_Type<br>1,1<br></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Competition Rules:\n - Don't cheat!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Contacts",
      "content": "<p>For any questions about the competitions or if you want to submit a use case for the Creativity evaluation, send an email to:</p>\n<li>gabriel.olympie@ekimetrics.com</li>\n<li>pierre.biousse@ekimetrics.com</li>\n<li>nicolas.chesneau@ekimetrics.com</li>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline And Details",
      "content": "This competition will be hosted during the month of April 2021, and will remain open for late submission after that.\n\nEach team will be able to submit at most 5 attempts per days, and select 2 of the attempts for the final submission.\n\nTest set is splitted randomly (50/50) between Public and Private test set, that will be used respectively for intermediate and final evaluation of the performance.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}