{
  "id": 332221,
  "title": "Correlation to target?",
  "url": "/competitions/amex-default-prediction/discussion/332221",
  "author_name": "",
  "post_date": "2022-06-20T21:43:49.723256200Z",
  "votes": 6,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Some public notebooks have published correlation plots of the predictors to the target. I don't think this is meaningful for a binary target. </p>\n<p>Am I missing something?</p>",
  "messages": [
    {
      "id": "1827149",
      "postDate": "06/20/2022 21:43:49",
      "content": "<p>Some public notebooks have published correlation plots of the predictors to the target. I don't think this is meaningful for a binary target. </p>\n<p>Am I missing something?</p>",
      "rawMarkdown": "Some public notebooks have published correlation plots of the predictors to the target. I don't think this is meaningful for a binary target. \n\nAm I missing something?",
      "votes": null
    },
    {
      "id": "1838942",
      "postDate": "07/01/2022 02:40:16",
      "content": "<p>Hi,<br>\nTake a look at <a href=\"https://towardsdatascience.com/the-search-for-categorical-correlation-a1cf7f1888c9\" target=\"_blank\">The Search for Categorical Correlation</a>. The association between the target and categorical features and correlation ratio (eta) between target and numerical features could unveil meaningful insights.<br>\nHere is a notebook example of the above article applied to this competition:<br>\n<a href=\"https://www.kaggle.com/code/mohammadrahmati/associations-and-correlations-useful-for-fe\" target=\"_blank\">Associations and Correlations</a></p>",
      "rawMarkdown": "Hi,\nTake a look at [The Search for Categorical Correlation](https://towardsdatascience.com/the-search-for-categorical-correlation-a1cf7f1888c9). The association between the target and categorical features and correlation ratio (eta) between target and numerical features could unveil meaningful insights.\nHere is a notebook example of the above article applied to this competition:\n[Associations and Correlations](https://www.kaggle.com/code/mohammadrahmati/associations-and-correlations-useful-for-fe)",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1838942,
      "author_name": "mohammadrahmati",
      "author_url": "",
      "post_date": "07/01/2022 02:40:16",
      "content": "<p>Hi,<br>\nTake a look at <a href=\"https://towardsdatascience.com/the-search-for-categorical-correlation-a1cf7f1888c9\" target=\"_blank\">The Search for Categorical Correlation</a>. The association between the target and categorical features and correlation ratio (eta) between target and numerical features could unveil meaningful insights.<br>\nHere is a notebook example of the above article applied to this competition:<br>\n<a href=\"https://www.kaggle.com/code/mohammadrahmati/associations-and-correlations-useful-for-fe\" target=\"_blank\">Associations and Correlations</a></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1827149": "Some public notebooks have published correlation plots of the predictors to the target. I don't think this is meaningful for a binary target. \n\nAm I missing something?",
    "1838942": "Hi,\nTake a look at [The Search for Categorical Correlation](https://towardsdatascience.com/the-search-for-categorical-correlation-a1cf7f1888c9). The association between the target and categorical features and correlation ratio (eta) between target and numerical features could unveil meaningful insights.\nHere is a notebook example of the above article applied to this competition:\n[Associations and Correlations](https://www.kaggle.com/code/mohammadrahmati/associations-and-correlations-useful-for-fe)"
  },
  "source": "meta"
}