{
  "id": 320186,
  "title": "My Idea(transformer model)",
  "url": "/competitions/h-and-m-personalized-fashion-recommendations/discussion/320186",
  "author_name": "Nozomi Maki",
  "post_date": "2022-04-20T12:15:50.466000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>The following supervised learning is used.</p>\n<p>As explanatory variables, I use a vector of sentences describing the items (using spaCy). Then, we set 12 items as the objective variables to be purchased in the next week (or later) from the past three months of purchases. It would be interesting to incorporate these into the transformer model.</p>\n<p>However, I do not have the time or the ability to implement the loss function settings or the order of the input and output items, so I am posting this here as an idea.</p>\n<p>If you are interested, I would appreciate it if you could implement it.</p>",
  "messages": [
    {
      "id": 1762069,
      "postDate": "2022-04-20T12:15:50.467Z",
      "content": "<p>The following supervised learning is used.</p>\n<p>As explanatory variables, I use a vector of sentences describing the items (using spaCy). Then, we set 12 items as the objective variables to be purchased in the next week (or later) from the past three months of purchases. It would be interesting to incorporate these into the transformer model.</p>\n<p>However, I do not have the time or the ability to implement the loss function settings or the order of the input and output items, so I am posting this here as an idea.</p>\n<p>If you are interested, I would appreciate it if you could implement it.</p>",
      "rawMarkdown": "The following supervised learning is used.\n\nAs explanatory variables, I use a vector of sentences describing the items (using spaCy). Then, we set 12 items as the objective variables to be purchased in the next week (or later) from the past three months of purchases. It would be interesting to incorporate these into the transformer model.\n\nHowever, I do not have the time or the ability to implement the loss function settings or the order of the input and output items, so I am posting this here as an idea.\n\nIf you are interested, I would appreciate it if you could implement it.\n"
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1762069": "The following supervised learning is used.\n\nAs explanatory variables, I use a vector of sentences describing the items (using spaCy). Then, we set 12 items as the objective variables to be purchased in the next week (or later) from the past three months of purchases. It would be interesting to incorporate these into the transformer model.\n\nHowever, I do not have the time or the ability to implement the loss function settings or the order of the input and output items, so I am posting this here as an idea.\n\nIf you are interested, I would appreciate it if you could implement it.\n"
  }
}