{
  "id": 61722,
  "title": "Scoring function for individual tracks",
  "url": "/competitions/trackml-particle-identification/discussion/61722",
  "author_name": "bilal2vec",
  "post_date": "2018-07-22T19:58:58.958000",
  "votes": 0,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hi,</p>\n\n<p>I was trying to score individual tracks and found that the track-ml scoring function doesn't give a very good representation of the quality of individual tracks. For example, the score of a track of one hit where the corresponding particle has ~7-8 hits is 1. This is not a problem when the score is averaged across all particles and events, but doesn't work well for determining the quality of individual tracks.</p>\n\n<p>Is there some other scoring function that would more accurately represent the quality of individual tracks?</p>\n\n<p>Thanks</p>",
  "messages": [
    {
      "id": 360805,
      "postDate": "2018-07-23T09:12:21.177Z",
      "content": "<blockquote>\n  <p>For example, the score of a track of one hit where the corresponding particle has ~7-8 hits is 1.</p>\n</blockquote>\n\n<p>I don't think this is the case, the score would be 0 as you get less than half of the hits of that particle.</p>",
      "rawMarkdown": "&gt; For example, the score of a track of one hit where the corresponding particle has ~7-8 hits is 1.\n\nI don't think this is the case, the score would be 0 as you get less than half of the hits of that particle."
    },
    {
      "id": 360595,
      "postDate": "2018-07-22T19:58:58.960Z",
      "content": "<p>Hi,</p>\n\n<p>I was trying to score individual tracks and found that the track-ml scoring function doesn't give a very good representation of the quality of individual tracks. For example, the score of a track of one hit where the corresponding particle has ~7-8 hits is 1. This is not a problem when the score is averaged across all particles and events, but doesn't work well for determining the quality of individual tracks.</p>\n\n<p>Is there some other scoring function that would more accurately represent the quality of individual tracks?</p>\n\n<p>Thanks</p>",
      "rawMarkdown": "Hi,\n\nI was trying to score individual tracks and found that the track-ml scoring function doesn't give a very good representation of the quality of individual tracks. For example, the score of a track of one hit where the corresponding particle has ~7-8 hits is 1. This is not a problem when the score is averaged across all particles and events, but doesn't work well for determining the quality of individual tracks.\n\nIs there some other scoring function that would more accurately represent the quality of individual tracks?\n\nThanks"
    },
    {
      "id": 360790,
      "postDate": "2018-07-23T08:38:14.830Z",
      "rawMarkdown": "",
      "votes": 1,
      "isDeleted": true
    }
  ],
  "comments": [
    {
      "id": 360805,
      "author_name": "CPMP",
      "author_url": "",
      "post_date": "2018-07-23T09:12:21.177000",
      "content": "<blockquote>\n  <p>For example, the score of a track of one hit where the corresponding particle has ~7-8 hits is 1.</p>\n</blockquote>\n\n<p>I don't think this is the case, the score would be 0 as you get less than half of the hits of that particle.</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 360790,
      "author_name": "",
      "author_url": "",
      "post_date": "2018-07-23T08:38:14.830000",
      "content": "",
      "votes": 1,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "360805": "&gt; For example, the score of a track of one hit where the corresponding particle has ~7-8 hits is 1.\n\nI don't think this is the case, the score would be 0 as you get less than half of the hits of that particle.",
    "360595": "Hi,\n\nI was trying to score individual tracks and found that the track-ml scoring function doesn't give a very good representation of the quality of individual tracks. For example, the score of a track of one hit where the corresponding particle has ~7-8 hits is 1. This is not a problem when the score is averaged across all particles and events, but doesn't work well for determining the quality of individual tracks.\n\nIs there some other scoring function that would more accurately represent the quality of individual tracks?\n\nThanks",
    "360790": ""
  }
}