{
  "fetched_at": "2026-10-20T08:06:42Z",
  "source_url": "https://www.kaggle.com/competitions/dmassignment1/data",
  "pages": [
    {
      "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!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p>This page contains two files that you are supposed to download and work on. They are as mentioned below:</p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>dataset.csv</strong> - the entire dataset</li>\n<li><strong>sample_submission.csv</strong> - a sample submission file in the correct format</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>This is the home page of the competition. As the tagline of the competition suggests your task is to classify the datapoints using clustering techniques. You have been provided with a dataset with 24 attributes and 1031 instances and your task is to classify the given dataset into 3 classes [0,1,2] using only <strong>Clustering</strong> algorithms. </p>\n<h2>A Brief Overview of Dataset</h2>\n<p>The given dataset contains the following 24 attributes:</p>\n<p><strong>id:</strong> Unique identity number</p>\n<p><strong>Account1:</strong> Accounts of type-1</p>\n<p><strong>Monthly Period:</strong> Duration in month</p>\n<p><strong>History:</strong> Types of client histories</p>\n<p><strong>Motvie:</strong> Types of client motives</p>\n<p><strong>Credit1:</strong> Credit amount</p>\n<p><strong>Account2:</strong> Accounts of type-2</p>\n<p><strong>Employment Period:</strong> Time Period of workers' employments</p>\n<p><strong>InstallmentRate:</strong> self-explanatory</p>\n<p><strong>Gender&Type:</strong> self-explanatory</p>\n<p><strong>Sponsors:</strong> Types of sponsors</p>\n<p><strong>Tenancy Period:</strong> Residence period</p>\n<p><strong>Plotsize:</strong> self-explanatory</p>\n<p><strong>Age:</strong> self-explanatory</p>\n<p><strong>Plan:</strong> Type of plan action</p>\n<p><strong>Housing:</strong> Type of residence owned</p>\n<p><strong>#Credits:</strong> Rate of credits</p>\n<p><strong>Post:</strong> His/Her job post</p>\n<p><strong>#Authorities:</strong> Total number of authorities engaged</p>\n<p><strong>Phone:</strong> If phone is available or not</p>\n<p><strong>Expatriate:</strong> Is he/she working for a foreign agency</p>\n<p><strong>InstallmentCredit:</strong> Credit received for installment</p>\n<p><strong>Yearly Period:</strong> Duration in years</p>\n<p><strong>Class:</strong> Target variable</p>\n\n<h2>Note:</h2>\n<p>These kinds of datasets are normally collected through online or offline forms. Hence the dataset may be imperfect in many ways. Thus identifying and correcting all of those imperfections will most likely give you better results. All the best!! =D</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<h2>Note:</h2>\n<p>Make sure that Class column in your submission file is in integer format, float Class values will fetch 0 score. E.g.: Class should be 1 and not 1.0.</p>\n\n<h2>Submission Format</h2>\n<p>You need to submit class labels of 856 unlabelled tuples of the dataset. The submission file must contain exactly two attributes: 'id' of the tuples and its corresponding 'Class' label.</p> \n<p>The submission file should contain a header and has the following format:</p>\n<pre>id,Class<br />id344,0<br /><span style=\"font-size: 14px; line-height: 1.4em;\">id744,1<br />id213,2<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">id949,1<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">etc.</span></pre>\n<p> For your reference a sample_submission.csv has been uploaded in the Data tab that will clarify any doubt regarding submission format.  </p>\n<hr />\n<p>You are given 5 days with 5 submissions on each day.</p>\n<p>Your submissions will be evaluated on 50% of the dataset to give your results on the public\nleaderboard. At the end of the competition, your selected submissions (you can select\nmaximum 2 submissions) will be evaluated on rest 50% of the data and will be shown on the\nprivate leaderboard. However, the final score will be based on your performance on 100%\ndata.</p>\n<p>The evaluation metric for this competition is <strong>Accuracy</strong>. The <strong>Accuracy</strong> score is given by:  \\[\\frac{\\#CorrectPredictions}{Total Labels(856)}\\] </p>\n<p><h2>Note:</h2> <strong>AFTER<strong> the competition ends, you need to upload the jupyter notebook that gave you your best result (corresponding to the private leaderboard) as a kernel on Kaggle. The result obtained on running your uploaded kernel must match your score on the private leaderboard. In case of mismatch, no marks will be awarded.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}