{
  "fetched_at": "2026-10-19T22:49:46Z",
  "source_url": "https://www.kaggle.com/competitions/ee5180-course-contest/data",
  "pages": [
    {
      "name": "data-description",
      "content": "# DataSet Description \n\nThe data is related with direct marketing campaigns of a Health Insurance Company. The marketing campaigns were based on phone calls. Often, more than one contact to the same client was required, in order to access if the insurance would be ('yes' or 1) or not ('no', or 0) subscribed.\n\n\n## Files\n\n*   **Insurance_Train.csv** - the training set\n*   **Insurance_Test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n## Columns\n\n**Client data:**\n\n* `Age` (numeric)\n* `Job`: type of job (categorical: 'admin.', 'blue-collar', 'entrepreneur', 'housemaid', 'management', 'retired', 'self-employed', 'services', 'student', 'technician', 'unemployed', 'unknown')\n* `Marital`: marital status (categorical: 'divorced', 'married', 'single', 'unknown' ; note: 'divorced' means divorced or widowed)\n* `Education`: (categorical: 'basic.4y', 'basic.6y', 'basic.9y', 'high.school', 'illiterate', 'professional.course', 'university.degree', 'unknown')\n* `Balance`: average yearly balance, in euros (numeric)\n* `Housing`: has housing loan? (categorical: 'no', 'yes', 'unknown')\n* `Loan`: has personal loan? (categorical: 'no', 'yes', 'unknown')\n\n**Related with the last contact of the current campaign:**\n\n* `Contact`: contact communication type (categorical:\n'cellular','telephone')\n* `Month`: last contact month of year (categorical: 'jan', 'feb', 'mar',\n…, 'nov', 'dec')\n* `Duration`: last contact duration, in seconds (numeric). Important\nnote: this attribute highly affects the output target (e.g., if\nduration=0 then y='no'). Yet, the duration is not known before a call\nis performed. Also, after the end of the call y is obviously known.\nThus, this input should only be included for benchmark purposes and\nshould be discarded if the intention is to have a realistic\npredictive model.\n\n**Other attributes:**\n\n* `Campaign`: number of contacts performed during this campaign and for\nthis client (numeric, includes last contact)\n* `Pdays`: number of days that passed by after the client was last\ncontacted from a previous campaign (numeric; 999 means client was not\npreviously contacted)\n* `Previous`: number of contacts performed before this campaign and for\nthis client (numeric)\n* `Poutcome`: outcome of the previous marketing campaign (categorical:\n'failure','nonexistent','success')\n\n**Output variable (desired target):**\n\ny - has the client subscribed a term deposit? (binary: 'yes', 'no')\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "**Problem Statement**\nInsurance firms have been running direct marketing efforts through telemarketing to encourage clients to apply for health insurance. So far, we have called all of our target clients, but to save money, we would like to limit the number of calls we make to those most likely to place purchases.\n\n**Task** \nAs a data scientist in the digital department of the insurance company, you are asked to output an attack list that predicts whether or not you will receive an order. Create the most accurate model possible. You need to analyse the data and match it with the quantitative result you get. We will see the analysis which you would perform on the data more than the accuracy of the model. Make all the analysis in a jupyter notebook using pandas and numpy library. \n\n**Rules**\n* You must use your team name for submissions\n* You are allowed to take inspiration from other sources. Copying any existing implementation directly without understanding will lead to disqualification from the contest. \n* You are allowed to use numpy, pandas and sklearn libraries. \n* Submit the code along with the application through the google form provided below. https://forms.gle/xhToyQ3QTtbUgefo7\n\n**Contact**\nIf you have any doubts, you can contact:\nVinayak - 9500180979\n\n\nIf you are new to Kaggle Competitions, you can check the below links, which will give you a brief overview of how kaggle competition works.\nHere is a handy link to Kaggle's [competition documentation](https://www.kaggle.com/docs/competitions), which includes, among other things, instructions on [submitting predictions](https://www.kaggle.com/docs/competitions#making-a-submission).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top; the page title appears above. For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have included below:\n\n---  d\n\nThe evaluation metric for this competition is [Mean F1-Score](https://en.wikipedia.org/wiki/F-score). The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision \\( \\text{p} \\) and recall \\( \\text{r} \\).\n\nPrecision is the ratio of true positives \\(\\text{tp}\\) to all predicted positives \\(\\text{tp} + \\text{fp}\\). Recall is the ratio of true positives \\(\\text{tp}\\) to all actual positives \\(\\text{tp} + \\text{fn}\\). The F1 score is given by:\n\n\\[ \\text{F1} = 2\\frac{\\text{p} \\cdot \\text{r}}{\\text{p}+\\text{r}}\\ \\ \\mathrm{where}\\ \\ \\text{p} = \\frac{\\text{tp}}{\\text{tp}+\\text{fp}},\\ \\ \\text{r} = \\frac{\\text{tp}}{\\text{tp}+\\text{fn}} \\]\n\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.\n\n## Submission Format\n\n**For every author in the dataset**, submission files should contain two columns: `AuthorId` and `DuplicateAuthorIds`. `DuplicateAuthorIds` should be a space-delimited list. Every `AuthorId` counts as its own duplicate, and every duplicate should be listed under each of its respective ids. For example, if you suspect author A, B, and C are the same, you should list `A,A B C`, `B,B A C`, `C,C A B`.\n\n\nThe file should contain a header and have the following format:\n```\nAuthorId,DuplicateAuthorIds\n1,1\n```",
      "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!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}