{
  "id": 261357,
  "title": "how did you improve your LB score??",
  "url": "/competitions/mlb-player-digital-engagement-forecasting/discussion/261357",
  "author_name": "",
  "post_date": "2021-08-04T11:12:34.269905200Z",
  "votes": 8,
  "comment_count": 2,
  "views": 0,
  "content": "<p>My idea was <br>\n・gamesStartedPitching lag feature<br>\n・tomorrow game exists or not</p>\n<p>◇gamesStartedPitching lag feature<br>\nI used \"gamesStartedPitching lag feature\". Starting pitcher sometimes pitch (one time per 4~5days) but they get high target1~4. I made sub model of predicting \"this pitcher will pitch tomorrow\". If this pitcher will pitch tomorrow, he will get high target.<br>\n\"This pitcher will pitch tomorrow\" is easy to predict, because MLB pitchers have rotation (almost of them pitch one time per 4~5days)</p>\n<p>◇tomorrow game exists or not<br>\nIf tomorrow game will not exist, target is low</p>\n<p>how did you improve your LB score??</p>",
  "messages": [
    {
      "id": "1446144",
      "postDate": "08/04/2021 11:12:34",
      "content": "<p>My idea was <br>\n・gamesStartedPitching lag feature<br>\n・tomorrow game exists or not</p>\n<p>◇gamesStartedPitching lag feature<br>\nI used \"gamesStartedPitching lag feature\". Starting pitcher sometimes pitch (one time per 4~5days) but they get high target1~4. I made sub model of predicting \"this pitcher will pitch tomorrow\". If this pitcher will pitch tomorrow, he will get high target.<br>\n\"This pitcher will pitch tomorrow\" is easy to predict, because MLB pitchers have rotation (almost of them pitch one time per 4~5days)</p>\n<p>◇tomorrow game exists or not<br>\nIf tomorrow game will not exist, target is low</p>\n<p>how did you improve your LB score??</p>",
      "rawMarkdown": "My idea was \n・gamesStartedPitching lag feature\n・tomorrow game exists or not\n\n◇gamesStartedPitching lag feature\nI used \"gamesStartedPitching lag feature\". Starting pitcher sometimes pitch (one time per 4~5days) but they get high target1~4. I made sub model of predicting \"this pitcher will pitch tomorrow\". If this pitcher will pitch tomorrow, he will get high target.\n\"This pitcher will pitch tomorrow\" is easy to predict, because MLB pitchers have rotation (almost of them pitch one time per 4~5days)\n\n◇tomorrow game exists or not\nIf tomorrow game will not exist, target is low\n\n\n\nhow did you improve your LB score??",
      "votes": null
    },
    {
      "id": "1449778",
      "postDate": "08/05/2021 00:40:56",
      "content": "<p>Predicting starting pitcher is smart. I have not thought of that</p>",
      "rawMarkdown": "Predicting starting pitcher is smart. I have not thought of that",
      "votes": null
    },
    {
      "id": "1455966",
      "postDate": "08/06/2021 18:42:41",
      "content": "<blockquote>\n  <p>◇tomorrow game exists or not</p>\n</blockquote>\n<p>I did it too. I added extra feature to help model learn period of player games. It is called <code>daysAfterPreviousGame</code>.</p>",
      "rawMarkdown": "> ◇tomorrow game exists or not\n\nI did it too. I added extra feature to help model learn period of player games. It is called `daysAfterPreviousGame`.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1449778,
      "author_name": "kaitehtzeng",
      "author_url": "",
      "post_date": "08/05/2021 00:40:56",
      "content": "<p>Predicting starting pitcher is smart. I have not thought of that</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1455966,
      "author_name": "sggpls",
      "author_url": "",
      "post_date": "08/06/2021 18:42:41",
      "content": "<blockquote>\n  <p>◇tomorrow game exists or not</p>\n</blockquote>\n<p>I did it too. I added extra feature to help model learn period of player games. It is called <code>daysAfterPreviousGame</code>.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1446144": "My idea was \n・gamesStartedPitching lag feature\n・tomorrow game exists or not\n\n◇gamesStartedPitching lag feature\nI used \"gamesStartedPitching lag feature\". Starting pitcher sometimes pitch (one time per 4~5days) but they get high target1~4. I made sub model of predicting \"this pitcher will pitch tomorrow\". If this pitcher will pitch tomorrow, he will get high target.\n\"This pitcher will pitch tomorrow\" is easy to predict, because MLB pitchers have rotation (almost of them pitch one time per 4~5days)\n\n◇tomorrow game exists or not\nIf tomorrow game will not exist, target is low\n\n\n\nhow did you improve your LB score??",
    "1449778": "Predicting starting pitcher is smart. I have not thought of that",
    "1455966": "> ◇tomorrow game exists or not\n\nI did it too. I added extra feature to help model learn period of player games. It is called `daysAfterPreviousGame`."
  },
  "source": "meta"
}