{
  "id": 118731,
  "title": "To perform timestamp alignment or not?",
  "url": "/competitions/ashrae-energy-prediction/discussion/118731",
  "author_name": "",
  "post_date": "2019-11-24T02:25:23.248420500Z",
  "votes": 1,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Based on several great findings (such as <a href=\"https://www.kaggle.com/nz0722/aligned-timestamp-lgbm-by-meter-type\">https://www.kaggle.com/nz0722/aligned-timestamp-lgbm-by-meter-type</a>), the local timestamp in weather_train and weather_test is not the local timestamp. </p>\n\n<p>Any thought on whether this is a valid feature engineering? For me it makes a lot of sense, but still curious on the effect.</p>",
  "messages": [
    {
      "id": "680104",
      "postDate": "11/24/2019 02:25:23",
      "content": "<p>Based on several great findings (such as <a href=\"https://www.kaggle.com/nz0722/aligned-timestamp-lgbm-by-meter-type\">https://www.kaggle.com/nz0722/aligned-timestamp-lgbm-by-meter-type</a>), the local timestamp in weather_train and weather_test is not the local timestamp. </p>\n\n<p>Any thought on whether this is a valid feature engineering? For me it makes a lot of sense, but still curious on the effect.</p>",
      "rawMarkdown": "Based on several great findings (such as https://www.kaggle.com/nz0722/aligned-timestamp-lgbm-by-meter-type), the local timestamp in weather_train and weather_test is not the local timestamp. \n\nAny thought on whether this is a valid feature engineering? For me it makes a lot of sense, but still curious on the effect.",
      "votes": null
    },
    {
      "id": "681308",
      "postDate": "11/26/2019 00:45:41",
      "content": "<p>I included this in my analysis in <a href=\"https://www.kaggle.com/purist1024/strategy-evaluation-what-helps-and-by-how-much/\">.Strategy evaluation: What Helps and How Much?</a>. The net improvement if you fix timestamps is about 0.4%, which is worth a few places on the LB.</p>",
      "rawMarkdown": "I included this in my analysis in [.Strategy evaluation: What Helps and How Much?](https://www.kaggle.com/purist1024/strategy-evaluation-what-helps-and-by-how-much/). The net improvement if you fix timestamps is about 0.4%, which is worth a few places on the LB.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 681308,
      "author_name": "purist1024",
      "author_url": "",
      "post_date": "11/26/2019 00:45:41",
      "content": "<p>I included this in my analysis in <a href=\"https://www.kaggle.com/purist1024/strategy-evaluation-what-helps-and-by-how-much/\">.Strategy evaluation: What Helps and How Much?</a>. The net improvement if you fix timestamps is about 0.4%, which is worth a few places on the LB.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "680104": "Based on several great findings (such as https://www.kaggle.com/nz0722/aligned-timestamp-lgbm-by-meter-type), the local timestamp in weather_train and weather_test is not the local timestamp. \n\nAny thought on whether this is a valid feature engineering? For me it makes a lot of sense, but still curious on the effect.",
    "681308": "I included this in my analysis in [.Strategy evaluation: What Helps and How Much?](https://www.kaggle.com/purist1024/strategy-evaluation-what-helps-and-by-how-much/). The net improvement if you fix timestamps is about 0.4%, which is worth a few places on the LB."
  },
  "source": "meta"
}