{
  "id": 329879,
  "title": "American Express - Default Prediction",
  "url": "/competitions/amex-default-prediction/discussion/329879",
  "author_name": "",
  "post_date": "2022-06-09T07:31:38.320117600Z",
  "votes": 6,
  "comment_count": 4,
  "views": 0,
  "content": "<p>whats the target variable here how can we start this can someone give an idea</p>",
  "messages": [
    {
      "id": "1815589",
      "postDate": "06/09/2022 07:31:38",
      "content": "<p>whats the target variable here how can we start this can someone give an idea</p>",
      "rawMarkdown": "whats the target variable here how can we start this can someone give an idea",
      "votes": null
    },
    {
      "id": "1815859",
      "postDate": "06/09/2022 14:55:14",
      "content": "<p>There are two provided files. The file <code>train_data.csv</code>, has all the customer information. There are up to 13 rows for each <code>customer_ID</code>. These are their 13 credit card statements in one year. Next there is a file named <code>train_labels.csv</code>. This file contains the 1's and 0's targets for the different <code>customer_ID</code>. Most teams aggregate the first file so that there is one row per customer with all the info. Then they merge the target onto this dataframe and start training.</p>",
      "rawMarkdown": "There are two provided files. The file `train_data.csv`, has all the customer information. There are up to 13 rows for each `customer_ID`. These are their 13 credit card statements in one year. Next there is a file named `train_labels.csv`. This file contains the 1's and 0's targets for the different `customer_ID`. Most teams aggregate the first file so that there is one row per customer with all the info. Then they merge the target onto this dataframe and start training.",
      "votes": null
    },
    {
      "id": "1816319",
      "postDate": "06/10/2022 05:12:50",
      "content": "<p>I do not know why someone downvoted you for this question <a href=\"https://www.kaggle.com/derindavid\" target=\"_blank\">@derindavid</a>, I have corrected for that :)</p>",
      "rawMarkdown": "I do not know why someone downvoted you for this question @derindavid, I have corrected for that :)",
      "votes": null
    },
    {
      "id": "1816501",
      "postDate": "06/10/2022 09:09:17",
      "content": "<p>Thank you <a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a> for the details. Let me try this. Thanks for the support <a href=\"https://www.kaggle.com/saurabhbagchi\" target=\"_blank\">@saurabhbagchi</a> </p>",
      "rawMarkdown": "Thank you @cdeotte for the details. Let me try this. Thanks for the support @saurabhbagchi",
      "votes": null
    },
    {
      "id": "1816503",
      "postDate": "06/10/2022 09:11:26",
      "content": "<p><a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a> , you are second in this competition.. I didnt expect that.. Thanks once again for the support and all the best.</p>",
      "rawMarkdown": "cdeotte , you are second in this competition.. I didnt expect that.. Thanks once again for the support and all the best.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1815859,
      "author_name": "cdeotte",
      "author_url": "",
      "post_date": "06/09/2022 14:55:14",
      "content": "<p>There are two provided files. The file <code>train_data.csv</code>, has all the customer information. There are up to 13 rows for each <code>customer_ID</code>. These are their 13 credit card statements in one year. Next there is a file named <code>train_labels.csv</code>. This file contains the 1's and 0's targets for the different <code>customer_ID</code>. Most teams aggregate the first file so that there is one row per customer with all the info. Then they merge the target onto this dataframe and start training.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1816319,
      "author_name": "saurabhbagchi",
      "author_url": "",
      "post_date": "06/10/2022 05:12:50",
      "content": "<p>I do not know why someone downvoted you for this question <a href=\"https://www.kaggle.com/derindavid\" target=\"_blank\">@derindavid</a>, I have corrected for that :)</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1816501,
      "author_name": "derindavid",
      "author_url": "",
      "post_date": "06/10/2022 09:09:17",
      "content": "<p>Thank you <a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a> for the details. Let me try this. Thanks for the support <a href=\"https://www.kaggle.com/saurabhbagchi\" target=\"_blank\">@saurabhbagchi</a> </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1816503,
      "author_name": "derindavid",
      "author_url": "",
      "post_date": "06/10/2022 09:11:26",
      "content": "<p><a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a> , you are second in this competition.. I didnt expect that.. Thanks once again for the support and all the best.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1815589": "whats the target variable here how can we start this can someone give an idea",
    "1815859": "There are two provided files. The file `train_data.csv`, has all the customer information. There are up to 13 rows for each `customer_ID`. These are their 13 credit card statements in one year. Next there is a file named `train_labels.csv`. This file contains the 1's and 0's targets for the different `customer_ID`. Most teams aggregate the first file so that there is one row per customer with all the info. Then they merge the target onto this dataframe and start training.",
    "1816319": "I do not know why someone downvoted you for this question @derindavid, I have corrected for that :)",
    "1816501": "Thank you @cdeotte for the details. Let me try this. Thanks for the support @saurabhbagchi",
    "1816503": "cdeotte , you are second in this competition.. I didnt expect that.. Thanks once again for the support and all the best."
  },
  "source": "meta"
}