I'm not sure how to go about submitting my winning model code. Kaggle guidelines for submitting models don't cover code competitions specifically, but they do say this: \"The core requirement is that you detail all the pieces needed by the host to reproduce your solution with the score your team achieved on the leaderboard within a reasonable margin.\"
\nhttps://www.kaggle.com/WinningModelDocumentationGuidelines
\nAs this is a code competition, the host already has all the pieces needed to run our models. It seems most likely that the competition sponsor will use our winning models in an environment like the one utilized in the competition, and will adapt our models to other environments if necessary. If winners modified their prediction mechanisms separately to run in different environments, that would remove the advantages of a common interface. So it seems that competitors don't have to do anything additional to submit their winning model code.
\nThe guidelines also recommend saving a trained model. That wouldn't be the best for my model, as it trains using the latest data.
\nAm I right that we don't need to do anything additional to submit our models in this competition? Kaggle's guidelines are a bit mysterious on this. If I'm missing something, please let me know.
\nBTW, I know about the summary and presentation, and I'm almost done with them.
", "messages": [ { "id": "1792410", "postDate": "05/17/2022 01:00:29", "content": "I'm not sure how to go about submitting my winning model code. Kaggle guidelines for submitting models don't cover code competitions specifically, but they do say this: \"The core requirement is that you detail all the pieces needed by the host to reproduce your solution with the score your team achieved on the leaderboard within a reasonable margin.\"
\nhttps://www.kaggle.com/WinningModelDocumentationGuidelines
\nAs this is a code competition, the host already has all the pieces needed to run our models. It seems most likely that the competition sponsor will use our winning models in an environment like the one utilized in the competition, and will adapt our models to other environments if necessary. If winners modified their prediction mechanisms separately to run in different environments, that would remove the advantages of a common interface. So it seems that competitors don't have to do anything additional to submit their winning model code.
\nThe guidelines also recommend saving a trained model. That wouldn't be the best for my model, as it trains using the latest data.
\nAm I right that we don't need to do anything additional to submit our models in this competition? Kaggle's guidelines are a bit mysterious on this. If I'm missing something, please let me know.
\nBTW, I know about the summary and presentation, and I'm almost done with them.
", "rawMarkdown": "I'm not sure how to go about submitting my winning model code. Kaggle guidelines for submitting models don't cover code competitions specifically, but they do say this: \"The core requirement is that you detail all the pieces needed by the host to reproduce your solution with the score your team achieved on the leaderboard within a reasonable margin.\"\n\nhttps://www.kaggle.com/WinningModelDocumentationGuidelines\n\nAs this is a code competition, the host already has all the pieces needed to run our models. It seems most likely that the competition sponsor will use our winning models in an environment like the one utilized in the competition, and will adapt our models to other environments if necessary. If winners modified their prediction mechanisms separately to run in different environments, that would remove the advantages of a common interface. So it seems that competitors don't have to do anything additional to submit their winning model code.\n\nThe guidelines also recommend saving a trained model. That wouldn't be the best for my model, as it trains using the latest data.\n\t\nAm I right that we don't need to do anything additional to submit our models in this competition? Kaggle's guidelines are a bit mysterious on this. If I'm missing something, please let me know.\n\nBTW, I know about the summary and presentation, and I'm almost done with them.", "votes": null }, { "id": "1792688", "postDate": "05/17/2022 07:49:35", "content": "You do not need to do anything else but sharing the notebook with the host 👀
", "rawMarkdown": "You do not need to do anything else but sharing the notebook with the host 👀", "votes": null }, { "id": "1793016", "postDate": "05/17/2022 14:29:03", "content": "Thanks! Wow, you got 1st place in Jane Street, so you should know what you're talking about.
", "rawMarkdown": "Thanks! Wow, you got 1st place in Jane Street, so you should know what you're talking about.", "votes": null }, { "id": "1793749", "postDate": "05/18/2022 07:49:24", "content": "Thanks Nathaniel for sharing! Well done to you and all the other winners.
", "rawMarkdown": "Thanks Nathaniel for sharing! Well done to you and all the other winners.", "votes": null }, { "id": "1793829", "postDate": "05/18/2022 09:08:25", "content": "hhh, I did the final submissions, so I was asked to share the notebook with the host.
", "rawMarkdown": "hhh, I did the final submissions, so I was asked to share the notebook with the host.", "votes": null }, { "id": "1794351", "postDate": "05/18/2022 18:01:15", "content": "Your welcome. Thank you for sponsoring the competition!
", "rawMarkdown": "Your welcome. Thank you for sponsoring the competition!", "votes": null } ], "comments": [ { "id": 1792688, "author_name": "yuanzhezhou", "author_url": "", "post_date": "05/17/2022 07:49:35", "content": "You do not need to do anything else but sharing the notebook with the host 👀
", "votes": null, "replies": [ { "id": 1793016, "author_name": "nathanrm", "author_url": "", "post_date": "05/17/2022 14:29:03", "content": "Thanks! Wow, you got 1st place in Jane Street, so you should know what you're talking about.
", "votes": null, "replies": [] }, { "id": 1793829, "author_name": "yuanzhezhou", "author_url": "", "post_date": "05/18/2022 09:08:25", "content": "hhh, I did the final submissions, so I was asked to share the notebook with the host.
", "votes": null, "replies": [] } ] }, { "id": 1793749, "author_name": "kierangarvey", "author_url": "", "post_date": "05/18/2022 07:49:24", "content": "Thanks Nathaniel for sharing! Well done to you and all the other winners.
", "votes": null, "replies": [ { "id": 1794351, "author_name": "nathanrm", "author_url": "", "post_date": "05/18/2022 18:01:15", "content": "Your welcome. Thank you for sponsoring the competition!
", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "1792410": "I'm not sure how to go about submitting my winning model code. Kaggle guidelines for submitting models don't cover code competitions specifically, but they do say this: \"The core requirement is that you detail all the pieces needed by the host to reproduce your solution with the score your team achieved on the leaderboard within a reasonable margin.\"\n\nhttps://www.kaggle.com/WinningModelDocumentationGuidelines\n\nAs this is a code competition, the host already has all the pieces needed to run our models. It seems most likely that the competition sponsor will use our winning models in an environment like the one utilized in the competition, and will adapt our models to other environments if necessary. If winners modified their prediction mechanisms separately to run in different environments, that would remove the advantages of a common interface. So it seems that competitors don't have to do anything additional to submit their winning model code.\n\nThe guidelines also recommend saving a trained model. That wouldn't be the best for my model, as it trains using the latest data.\n\t\nAm I right that we don't need to do anything additional to submit our models in this competition? Kaggle's guidelines are a bit mysterious on this. If I'm missing something, please let me know.\n\nBTW, I know about the summary and presentation, and I'm almost done with them.", "1792688": "You do not need to do anything else but sharing the notebook with the host 👀", "1793016": "Thanks! Wow, you got 1st place in Jane Street, so you should know what you're talking about.", "1793749": "Thanks Nathaniel for sharing! Well done to you and all the other winners.", "1793829": "hhh, I did the final submissions, so I was asked to share the notebook with the host.", "1794351": "Your welcome. Thank you for sponsoring the competition!" }, "source": "meta" }