{
  "fetched_at": "2026-10-19T22:26:39Z",
  "source_url": "https://www.kaggle.com/competitions/aicvs-bank/data",
  "pages": [
    {
      "name": "rules",
      "content": " - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p>The data is related with direct marketing campaigns of a Portuguese banking institution. 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 product (bank term deposit) would be ('yes') or not ('no') subscribed. The classification goal is to predict if the client will subscribe (yes/no) a term deposit (variable y).</p> \n\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - the training set</li>\n<li><strong>test.csv</strong> - the test set</li>\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n\n<h2>Attribute Information</h2>\n\n<h3>Input variables:</h3>\n<h4>bank client data:</h4>\n<li><strong>id</strong> (numeric)</li>\n<li><strong>age</strong> (numeric)</li>\n<li><strong>job</strong> : type of job (categorical: 'admin.', 'blue-collar', 'entrepreneur', 'housemaid', 'management', 'retired', 'self-employed', 'services', 'student', 'technician', 'unemployed', 'unknown') </li>\n<li><strong>marital</strong> : marital status (categorical: 'divorced','married','single','unknown'; note: 'divorced' means divorced or widowed)</li>\n<li><strong>education</strong> (categorical: 'basic.4y', 'basic.6y', 'basic.9y', 'high.school', 'illiterate', 'professional.course', 'university.degree', 'unknown')</li>\n<li><strong>default</strong>: has credit in default? (categorical: 'no','yes','unknown')</li>\n<li><strong>housing</strong>: has housing loan? (categorical: 'no','yes','unknown')</li>\n<li><strong>loan</strong>: has personal loan? (categorical: 'no','yes','unknown')</li>\n<h4>related with the last contact of the current campaign:</h4>\n<li><strong>contact</strong>: contact communication type (categorical: 'cellular','telephone')</li>\n<li><strong>month</strong>: last contact month of year (categorical: 'jan', 'feb', 'mar', ..., 'nov', 'dec')</li>\n<li><strong>day_of_week</strong>: last contact day of the week (categorical: 'mon','tue','wed','thu','fri')</li>\n<li><strong>duration</strong>: last contact duration, in seconds (numeric). Important note: this attribute highly affects the output target (e.g., if duration=0 then y='no'). Yet, the duration is not known before a call is performed. Also, after the end of the call y is obviously known. Thus, this input should only be included for benchmark purposes and should be discarded if the intention is to have a realistic predictive model.</li>\n<h4>other attributes:</h4>\n<li><strong>campaign</strong>: number of contacts performed during this campaign and for this client (numeric, includes last contact)</li>\n<li><strong>pdays</strong>: number of days that passed by after the client was last contacted from a previous campaign (numeric; 999 means client was not previously contacted)</li>\n<li><strong>previous</strong>: number of contacts performed before this campaign and for this client (numeric)</li>\n<li><strong>poutcome</strong>: outcome of the previous marketing campaign (categorical: 'failure', 'nonexistent', 'success')</li>\n<h4>social and economic context attributes</h4>\n<li><strong>emp.var.rate</strong>: employment variation rate - quarterly indicator (numeric)</li>\n<li><strong>cons.price.idx</strong>: consumer price index - monthly indicator (numeric)</li>\n<li><strong>cons.conf.idx</strong>: consumer confidence index - monthly indicator (numeric)</li>\n<li><strong>euribor3m</strong>: euribor 3 month rate - daily indicator (numeric)</li>\n<li><strong>nr.employed</strong>: number of employees - quarterly indicator (numeric)</li>\n\n<h3>Output variable (desired target)</h3>\n<li><strong>y</strong>: has the client subscribed a term deposit? (binary: 'yes','no')</li>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>Welcome to AICVS's Bank Client Kaggle Competition</h2>\n<p>Our competition is on a UCI Machine Learning Dataset called Bank Marketing Data Set. The data is related with direct marketing campaigns (phone calls) of a Portuguese banking institution. The classification goal is to predict if the client will subscribe a term deposit (variable y).</p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<h2>Competition Description</h2>\n\n<p>The data is related with direct marketing campaigns of a Portuguese banking institution. 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 product (bank term deposit) would be ('yes') or not ('no') subscribed. The classification goal is to predict if the client will subscribe (yes/no) a term deposit (variable y).</p>\n\n<p>Due to the nature of the dataset, you will have to deal with two concepts: high dimensionality of the dataset, which means that you will have to reduce the features to low dimension (reduce the number of features) and you will also have to deal with unbalanced classes, ie, when there is a disproportionately high amount of samples in one of the classes. You can use a simple classification technique, like logistic regression that we used in the Titanic Dataset for classification on the pre-processed dataset.</p>\n\n<h2>Acknowledgements</h2>\n<p>This dataset has been taken from the UCI Machine Learning Dataset, particularly the bank-full.csv for an inclass competition</h2>\n\n<h2>Goal</h2>\n<p>The classification goal is to predict if the client will subscribe (yes/no) a term deposit (variable y). For each sample (row) in the test set, you must predict a 0 or 1 value for the variable.</p>\n\n<h2>Metric</h2>\n<p>Your score is the percentage of clients you correctly predict. This is known simply as \"accuracy”.</p>\n\n<h2>Submission File Format</h2>\n<p>For every author in the dataset, submission files should contain two columns: Id and y. y is the order to access if the product (bank term deposit) would be ('yes') or not ('no') subscribed.\n</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>Id,y<br />1,yes<br /><span style=\"font-size: 14px; line-height: 1.4em;\">2,no<br />3,no<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">4,yes<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">etc.</span></pre>\n\n<p>You can download an example submission file (gender_submission.csv) on the Data page.</p>\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}