{
  "fetched_at": "2026-10-19T21:50:08Z",
  "source_url": "https://www.kaggle.com/competitions/decsc-131-case-study-2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "This is the classic marketing bank dataset uploaded originally in the UCI Machine Learning Repository. The dataset gives you information about a marketing campaign of a financial institution in which you will have to analyze in order to find ways to look for future strategies in order to improve future marketing campaigns for the bank.\n\n## Files\n\n*   **train_bank_marketing.csv** - the training set\n*   **test_bank_marketing.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n\n## Input variables:\n\n**Bank Client Data:**\n\n   1 - age (numeric)\n\n   2 - job : type of job (categorical: \"admin.\",\"blue-collar\",\"entrepreneur\",\"housemaid\",\"management\",\"retired\",\"self-employed\",\"services\",\"student\",\"technician\",\"unemployed\",\"unknown\")\n\n   3 - marital : marital status (categorical: \"divorced\",\"married\",\"single\",\"unknown\"; note: \"divorced\" means divorced or widowed)\n\n   4 - education (categorical: \"basic.4y\",\"basic.6y\",\"basic.9y\",\"high.school\",\"illiterate\",\"professional.course\",\"university.degree\",\"unknown\")\n\n   5 - default: has credit in default? (categorical: \"no\",\"yes\",\"unknown\")\n\n   6 - housing: has housing loan? (categorical: \"no\",\"yes\",\"unknown\")\n\n   7 - loan: has personal loan? (categorical: \"no\",\"yes\",\"unknown\")\n\n**Related with the last contact of the current campaign:**\n\n   8 - contact: contact communication type (categorical: \"cellular\",\"telephone\") \n\n   9 - month: last contact month of year (categorical: \"jan\", \"feb\", \"mar\", ..., \"nov\", \"dec\")\n\n  10 - day_of_week: last contact day of the week (categorical: \"mon\",\"tue\",\"wed\",\"thu\",\"fri\")\n\n  11 - duration: last contact duration, in seconds (numeric)\n  \n**Marketing-related attributes:**\n\n  12 - campaign: number of contacts performed during this campaign and for this client (numeric, includes last contact)\n\n  13 - pdays: number of days that passed by after the client was last contacted from a previous campaign (numeric; 999 means client was not previously contacted)\n\n  14 - previous: number of contacts performed before this campaign and for this client (numeric)\n\n  15 - poutcome: outcome of the previous marketing campaign (categorical: \"failure\",\"nonexistent\",\"success\")\n \n**Social and economic context attributes:**\n\n  16 - emp.var.rate: employment variation rate - quarterly indicator (numeric)\n\n  17 - cons.price.idx: consumer price index - monthly indicator (numeric)     \n\n  18 - cons.conf.idx: consumer confidence index - monthly indicator (numeric)     \n\n  19 - euribor3m: euribor 3 month rate - daily indicator (numeric)\n\n  20 - nr.employed: number of employees - quarterly indicator (numeric)\n\n**Output variable (desired target):**\n\n  21 - y - has the client subscribed a term deposit? (binary: \"yes\",\"no\")\n\n**Missing Attribute Values:** There are several missing values in some categorical attributes, all coded with the \"unknown\" label. These missing values can be treated as a possible class label (i.e. treat them as \"no\" values).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "\n## Bank Marketing Case\n\nFind the best strategies to improve for the next marketing campaign. How can the financial institution have a greater effectiveness for future marketing campaigns? In order to answer this, we have to analyze the last marketing campaign the bank performed and identify the patterns that will help us find conclusions in order to develop future strategies.\n\n\nIn this competition, we would be applying all of the machine learning models that we have learned from the course in order to be able to predict who among the customers from the data tends to have subscribed to a term deposit or not. By being able to accomplish this, we are able to identify what are the indicators that are associated with customers making a purchase.\n\n## Acknowledgements\n\nS. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, In press, http://dx.doi.org/10.1016/j.dss.2014.03.001",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "## Model Performance Evaluation\n\nThe model's predictions would be evaluated on the basis of **classification accuracy**, which refers to the sum of true positives and true negatives divided by the total number of observations in the dataset.\n\nLearning teams that would get the best model performance on the **private leaderboard** (which contains all of the test data) would get a perfect score on the second case study. Each team would be ranked at the end of the competition, and the score of each team in the second case study would be based from the following imputation table:\n\n| Rank | Case Study Score |\n| --- | --- |\n| 1 | 100  |\n| 2 | 95  |\n| 3 | 90 |\n| 4 | 85 |\n| 5 | 80  |\n\nThroughout the competition, teams would know how their model is performing relative to other learners in the class through the public leaderboard. The public leaderboard only evaluates the model to a random proportion of observations on the test set, so that students would not game the system. The final rankings of all teams would be dependent on the rankings shown on the **private leaderboard**. Hence, student team's rankings may go higher or lower relative to their rank on the **public leaderboard**.\n\n## Submission Format\n\n**For every customer in the dataset**, submission files should contain two columns: `id` and `y`.  `y` refers to the team's predictions for each customer on the test set.\n\nThe CSV file should contain a header and have the following format:\n```\nid, y\n1,1\n2,0\n3,0\n4,1\n5,0\n```\n\nDo take note that the test set has 10297 rows. Make sure that your team is uploading a CSV file containing predictions for 10297 customers.\n\nStudents are allowed to upload up to 20 predictions for the test set each day. Once this limit has been breached, the team has to wait for the day to elapse before being able to upload a submission once again. Each submitted predictions would be evaluated on the public leaderboard up until May 17, 2021 (11:59 PM). No more submissions would be accepted by the system beyond this time. The results on the private leaderboard would be up by May 18, 2021 (12:00 NN).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}