The data supplement is being updated again to give you an opportunity to factor the recent market volatility into your models. The update should be live within the next hour.
\nThere will still be one more update to the supplemental_train.csv on the original schedule (after the submission deadline), which will cover the remainder of the period up until the submission deadline. Barring any missing data, the final copy of supplemental_train.csv will end right before the forecasting phase test set data begins.
", "messages": [ { "id": 1665533, "postDate": "2022-01-26T23:30:41.940Z", "content": "The data supplement is being updated again to give you an opportunity to factor the recent market volatility into your models. The update should be live within the next hour.
\nThere will still be one more update to the supplemental_train.csv on the original schedule (after the submission deadline), which will cover the remainder of the period up until the submission deadline. Barring any missing data, the final copy of supplemental_train.csv will end right before the forecasting phase test set data begins.
", "rawMarkdown": "The data supplement is being updated again to give you an opportunity to factor the recent market volatility into your models. The update should be live within the next hour.\n\nThere will still be one more update to the supplemental_train.csv on the original schedule (after the submission deadline), which will cover the remainder of the period up until the submission deadline. Barring any missing data, the final copy of supplemental_train.csv will end right before the forecasting phase test set data begins.", "votes": 15 }, { "id": 1665545, "postDate": "2022-01-27T00:12:15.580Z", "content": "Thank you for giving us the opportunity to have 'live' algo in those markets without risking a cent.
", "rawMarkdown": "Thank you for giving us the opportunity to have 'live' algo in those markets without risking a cent. ", "votes": 1 }, { "id": 1667831, "postDate": "2022-01-29T01:17:11.377Z", "content": "@sohier Hi, every time you updated the supplimental_train.csv, I encountered the problem to load the other dataset. For instance, I am using the asset_detail.csv. Right after you updated the supplementary train data set, my code says that \"[Errno 2] No such file or directory: '../input/g-research-crypto-forecasting/asset_details.csv'\".
\nI am worried that my code will fail to run after you update the supplementary train dataset for the evaluation. Is this something that I will have to worry about?
", "rawMarkdown": "@sohier Hi, every time you updated the supplimental_train.csv, I encountered the problem to load the other dataset. For instance, I am using the asset_detail.csv. Right after you updated the supplementary train data set, my code says that \"[Errno 2] No such file or directory: '../input/g-research-crypto-forecasting/asset_details.csv'\". \n\nI am worried that my code will fail to run after you update the supplementary train dataset for the evaluation. Is this something that I will have to worry about? ", "votes": 2, "replies": [ { "id": 1667862, "postDate": "2022-01-29T02:38:55.993Z", "content": "same case happened to me twice
", "rawMarkdown": "same case happened to me twice", "votes": 1 } ] }, { "id": 1672754, "postDate": "2022-02-02T09:18:27.450Z", "content": "@sohier can we choose the final submission after the deadline. as some of the submission has been scored after the deadline…
", "rawMarkdown": "@sohier can we choose the final submission after the deadline. as some of the submission has been scored after the deadline...", "replies": [ { "id": 1672778, "postDate": "2022-02-02T09:46:00.727Z", "content": "doubt it, part of the skill in a kaggle comp is in selecting the best solution
", "rawMarkdown": "doubt it, part of the skill in a kaggle comp is in selecting the best solution" } ] }, { "id": 1669380, "postDate": "2022-01-30T16:04:10.383Z", "content": "Hi, I'm a bit concern about some spikes in the data and more specifically in the recent one. For instance take the asset 8 from 2022-01-03 02:31:00 to 2022-01-04 20:10:00 (or 1641177060 to 1641327000) you will find quit some strange patterns for the Close and Low price (c.f. the chart).
\nIs this normal or there is indeed something going on?
", "rawMarkdown": "Hi, I'm a bit concern about some spikes in the data and more specifically in the recent one. For instance take the asset 8 from 2022-01-03 02:31:00 to 2022-01-04 20:10:00 (or 1641177060 to 1641327000) you will find quit some strange patterns for the Close and Low price (c.f. the chart).\n\n\n\nIs this normal or there is indeed something going on?" }, { "id": 1665553, "postDate": "2022-01-27T00:47:26.867Z", "content": "Hi @sohier , thanks for the update. Would it be possible to have one more round of update before the final submission deadline (maybe a day ago)? It would be helpful if someone does not want to train the model in the inference kernel and train it in a separate kernel with the recent possible data.
", "rawMarkdown": "Hi @sohier , thanks for the update. Would it be possible to have one more round of update before the final submission deadline (maybe a day ago)? It would be helpful if someone does not want to train the model in the inference kernel and train it in a separate kernel with the recent possible data." }, { "id": 1666224, "postDate": "2022-01-27T15:14:41.177Z", "rawMarkdown": "", "isDeleted": true } ], "comments": [ { "id": 1665545, "author_name": "Lucas Morin", "author_url": "", "post_date": "2022-01-27T00:12:15.580000", "content": "Thank you for giving us the opportunity to have 'live' algo in those markets without risking a cent.
", "votes": 1, "replies": [] }, { "id": 1667831, "author_name": "gyugyugyu", "author_url": "", "post_date": "2022-01-29T01:17:11.377000", "content": "@sohier Hi, every time you updated the supplimental_train.csv, I encountered the problem to load the other dataset. For instance, I am using the asset_detail.csv. Right after you updated the supplementary train data set, my code says that \"[Errno 2] No such file or directory: '../input/g-research-crypto-forecasting/asset_details.csv'\".
\nI am worried that my code will fail to run after you update the supplementary train dataset for the evaluation. Is this something that I will have to worry about?
", "votes": 2, "replies": [ { "id": 1667862, "author_name": "Yue Sun", "author_url": "", "post_date": "2022-01-29T02:38:55.993000", "content": "same case happened to me twice
", "votes": 1, "replies": [] } ] }, { "id": 1672754, "author_name": "Pranay Joshi", "author_url": "", "post_date": "2022-02-02T09:18:27.450000", "content": "@sohier can we choose the final submission after the deadline. as some of the submission has been scored after the deadline…
", "votes": 0, "replies": [ { "id": 1672778, "author_name": "Marco Gorelli", "author_url": "", "post_date": "2022-02-02T09:46:00.727000", "content": "doubt it, part of the skill in a kaggle comp is in selecting the best solution
", "votes": 0, "replies": [] } ] }, { "id": 1669380, "author_name": "iiyadmea", "author_url": "", "post_date": "2022-01-30T16:04:10.383000", "content": "Hi, I'm a bit concern about some spikes in the data and more specifically in the recent one. For instance take the asset 8 from 2022-01-03 02:31:00 to 2022-01-04 20:10:00 (or 1641177060 to 1641327000) you will find quit some strange patterns for the Close and Low price (c.f. the chart).
\nIs this normal or there is indeed something going on?
", "votes": 0, "replies": [] }, { "id": 1665553, "author_name": "Indranil Bhattacharya", "author_url": "", "post_date": "2022-01-27T00:47:26.867000", "content": "Hi @sohier , thanks for the update. Would it be possible to have one more round of update before the final submission deadline (maybe a day ago)? It would be helpful if someone does not want to train the model in the inference kernel and train it in a separate kernel with the recent possible data.
", "votes": 0, "replies": [] }, { "id": 1666224, "author_name": "", "author_url": "", "post_date": "2022-01-27T15:14:41.177000", "content": "", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "1665533": "The data supplement is being updated again to give you an opportunity to factor the recent market volatility into your models. The update should be live within the next hour.\n\nThere will still be one more update to the supplemental_train.csv on the original schedule (after the submission deadline), which will cover the remainder of the period up until the submission deadline. Barring any missing data, the final copy of supplemental_train.csv will end right before the forecasting phase test set data begins.", "1665545": "Thank you for giving us the opportunity to have 'live' algo in those markets without risking a cent. ", "1667831": "@sohier Hi, every time you updated the supplimental_train.csv, I encountered the problem to load the other dataset. For instance, I am using the asset_detail.csv. Right after you updated the supplementary train data set, my code says that \"[Errno 2] No such file or directory: '../input/g-research-crypto-forecasting/asset_details.csv'\". \n\nI am worried that my code will fail to run after you update the supplementary train dataset for the evaluation. Is this something that I will have to worry about? ", "1672754": "@sohier can we choose the final submission after the deadline. as some of the submission has been scored after the deadline...", "1669380": "Hi, I'm a bit concern about some spikes in the data and more specifically in the recent one. For instance take the asset 8 from 2022-01-03 02:31:00 to 2022-01-04 20:10:00 (or 1641177060 to 1641327000) you will find quit some strange patterns for the Close and Low price (c.f. the chart).\n\n\n\nIs this normal or there is indeed something going on?", "1665553": "Hi @sohier , thanks for the update. Would it be possible to have one more round of update before the final submission deadline (maybe a day ago)? It would be helpful if someone does not want to train the model in the inference kernel and train it in a separate kernel with the recent possible data.", "1666224": "" } }