Thank you all for your hard work in this competition and congratulations to our winners! We know this competition had a shakeup at the end, which keeps things exciting at the end, as well as reinforcing the adage some of you have also mentioned \"Trust the CV.\"
\n\nAnd a continued congratulation to the many of you may reach a new tier because of this competition, as well as far more of you for which this was your first competitions.
\n\nWe're also continually pleased to see how Kaggle Competitions serve as a great medium and vehicle through which the greater data science community can learn and develop their machine learning abilities and skills. Beginners and experts can come together to start, grow, and succeed. And thanks to the many of you who have shared your solutions in the forums for others to learn from.
\n\nWe also would like to give special thanks to Bertrand from LANL, Laura from Purdue, and additional hosts from Penn State and the DoE for allowing us to run this competition. We hope to be able to work with them in the future.
\n\nWe've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, please contact compliance. Please fill in all the fields honestly.
\n\nThe top potential winning teams have been contacted via email to provide their winning solutions for sponsor review. Should we need to move down the leaderboard for any reason, we will do so and continue to make contact with subsequent teams.
\n\nYou should see your points and medals awarded soon, however it may take a few hours to propagate through.
\n\nWe hope to see you in our next competitions!
\n\nHappy Modeling!
", "messages": [ { "id": 544720, "postDate": "2019-06-05T20:06:25.523Z", "content": "A quick suggestion. Kaggle should have the following statement that each sponsor must endorse prior to the competition: \"To the best of our knowledge, Test set has never been released to the public in any shape or form.\"
", "rawMarkdown": "A quick suggestion. Kaggle should have the following statement that each sponsor must endorse prior to the competition: \"To the best of our knowledge, Test set has never been released to the public in any shape or form.\"", "votes": 14 }, { "id": 544697, "postDate": "2019-06-05T19:29:43.500Z", "content": "Thank you all for your hard work in this competition and congratulations to our winners! We know this competition had a shakeup at the end, which keeps things exciting at the end, as well as reinforcing the adage some of you have also mentioned \"Trust the CV.\"
\n\nAnd a continued congratulation to the many of you may reach a new tier because of this competition, as well as far more of you for which this was your first competitions.
\n\nWe're also continually pleased to see how Kaggle Competitions serve as a great medium and vehicle through which the greater data science community can learn and develop their machine learning abilities and skills. Beginners and experts can come together to start, grow, and succeed. And thanks to the many of you who have shared your solutions in the forums for others to learn from.
\n\nWe also would like to give special thanks to Bertrand from LANL, Laura from Purdue, and additional hosts from Penn State and the DoE for allowing us to run this competition. We hope to be able to work with them in the future.
\n\nWe've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, please contact compliance. Please fill in all the fields honestly.
\n\nThe top potential winning teams have been contacted via email to provide their winning solutions for sponsor review. Should we need to move down the leaderboard for any reason, we will do so and continue to make contact with subsequent teams.
\n\nYou should see your points and medals awarded soon, however it may take a few hours to propagate through.
\n\nWe hope to see you in our next competitions!
\n\nHappy Modeling!
", "rawMarkdown": "Thank you all for your hard work in this competition and congratulations to our winners! We know this competition had a shakeup at the end, which keeps things exciting at the end, as well as reinforcing the adage some of you have also mentioned \"Trust the CV.\"\n\nAnd a continued congratulation to the many of you may reach a new tier because of this competition, as well as far more of you for which this was your first competitions.\n\nWe're also continually pleased to see how Kaggle Competitions serve as a great medium and vehicle through which the greater data science community can learn and develop their machine learning abilities and skills. Beginners and experts can come together to start, grow, and succeed. And thanks to the many of you who have shared your solutions in the forums for others to learn from.\n\nWe also would like to give special thanks to Bertrand from LANL, Laura from Purdue, and additional hosts from Penn State and the DoE for allowing us to run this competition. We hope to be able to work with them in the future.\n\nWe've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, please contact [compliance][1]. Please fill in all the fields honestly.\n\nThe top potential winning teams have been contacted via email to provide their winning solutions for sponsor review. Should we need to move down the leaderboard for any reason, we will do so and continue to make contact with subsequent teams.\n\nYou should see your points and medals awarded soon, however it may take a few hours to propagate through.\n\nWe hope to see you in our next competitions!\n\nHappy Modeling!\n\n [1]: https://www.kaggle.com/compliance", "votes": 13 }, { "id": 546310, "postDate": "2019-06-06T13:08:56.473Z", "content": "Thankyou, I enjoyed the competition but I find the 100% positive spin you have put on this is almost Trumpian IMHO. Kaggle hasn't addressed or rebutted a single criticism in the discussions section which is bad form.
\n\nhttps://www.kaggle.com/c/LANL-Earthquake-Prediction/discussion/94411
\n\nMFCC with/without filtering seemed one of the best angles of attack so perhaps after they have researched it they can give us 100s of complete earthquakes using this method as the data would be quite small. Perhaps adding a transverse sensor rather than the single one they use now might also be useful.
", "rawMarkdown": "Thankyou, I enjoyed the competition but I find the 100% positive spin you have put on this is almost Trumpian IMHO. Kaggle hasn't addressed or rebutted a single criticism in the discussions section which is bad form. \n\nhttps://www.kaggle.com/c/LANL-Earthquake-Prediction/discussion/94411\n\nMFCC with/without filtering seemed one of the best angles of attack so perhaps after they have researched it they can give us 100s of complete earthquakes using this method as the data would be quite small. Perhaps adding a transverse sensor rather than the single one they use now might also be useful.\n", "votes": 4, "replies": [ { "id": 546391, "postDate": "2019-06-06T14:38:04.917Z", "content": "Hey @Scriptus -
\n\nI don't think you're being very charitable here. We work very hard balancing our time launching new competitions vs addressing all possible concerns. There are approximately 10,000x more active Kagglers than there are Kaggle Data Scientists, which necessitates some degree of balance.
\n\nNearly all competitions have opportunities for improvement identified after thousands of data scientists have spent months scrutinizing them. We always review and try to improve. We don't though, always have the bandwidth to respond to every comment or concern.
\n\nOne reason I haven't responded to the thread you posted - the #4 point in the OP was caused by switching the metric for competition after the kernel submission (which happened pre-launch). The tag didn't update after the fact, even when the Kernel was re-run. This is a submitted bug, but very low priority since this edge case almost never happens. When someone adds that to a long list of concerns and calls it sloppy, I tend to think the comment was more venting than a good-faith effort to improve things, and those discussions generally aren't time well spent.
", "rawMarkdown": "Hey @Scriptus -\n\nI don't think you're being very charitable here. We work very hard balancing our time launching new competitions vs addressing all possible concerns. There are approximately 10,000x more active Kagglers than there are Kaggle Data Scientists, which necessitates some degree of balance.\n\nNearly all competitions have opportunities for improvement identified after thousands of data scientists have spent months scrutinizing them. We _always_ review and try to improve. We don't though, always have the bandwidth to respond to every comment or concern.\n\nOne reason I haven't responded to the thread you posted - the #4 point in the OP was caused by switching the metric for competition after the kernel submission (which happened pre-launch). The tag didn't update after the fact, even when the Kernel was re-run. This is a submitted bug, but very low priority since this edge case almost never happens. When someone adds that to a long list of concerns and calls it sloppy, I tend to think the comment was more venting than a good-faith effort to improve things, and those discussions generally aren't time well spent.", "votes": 2 }, { "id": 546408, "postDate": "2019-06-06T14:55:25.883Z", "content": "Hi @inversion - we all appreciate the work you do (even though it might not seem so sometimes). The main point for me at least is that answers to questions completely dried up months ago which seems daft considering the length of the competition.
\n\nMost of us give feedback not to moan but to make Kaggle better - it benefits us all in the end.
", "rawMarkdown": "Hi @inversion - we all appreciate the work you do (even though it might not seem so sometimes). The main point for me at least is that answers to questions completely dried up months ago which seems daft considering the length of the competition. \n\nMost of us give feedback not to moan but to make Kaggle better - it benefits us all in the end.\n\n\n", "votes": 6 }, { "id": 546412, "postDate": "2019-06-06T15:04:43.113Z", "content": "@scirpus I agree with you. This was an unusually long competition, and you are totally right in that engagement dropped off during the second half. This is not ideal at all, and in fact, I took this back to the team as a \"we can do better\" item this past Tuesday.
\n\nI'm be OOO for a few days starting this afternoon, but will get back to these main points next week.
", "rawMarkdown": "@scirpus I agree with you. This was an unusually long competition, and you are totally right in that engagement dropped off during the second half. This is not ideal at all, and in fact, I took this back to the team as a \"we can do better\" item this past Tuesday. \n\nI'm be OOO for a few days starting this afternoon, but will get back to these main points next week. ", "votes": 3 }, { "id": 546445, "postDate": "2019-06-06T15:37:33.113Z", "content": "Thanks for the response. I have always appreciated your contributions to Kaggle - not just as an employee of Kaggle but also when you were on the other side of the fence.
", "rawMarkdown": "Thanks for the response. I have always appreciated your contributions to Kaggle - not just as an employee of Kaggle but also when you were on the other side of the fence. ", "votes": 1 }, { "id": 546582, "postDate": "2019-06-06T17:41:53.733Z", "content": "@scirpus Likewise!
", "rawMarkdown": "@scirpus Likewise!", "votes": 1 } ] }, { "id": 550499, "postDate": "2019-06-11T17:15:30.940Z", "content": "Congratulation to the winners!!!
", "rawMarkdown": "Congratulation to the winners!!!", "votes": 1 }, { "id": 546058, "postDate": "2019-06-06T07:59:37.057Z", "content": "Congratulations to all participants!
", "rawMarkdown": "Congratulations to all participants!", "votes": 1 }, { "id": 2457484, "postDate": "2023-09-27T00:57:55.517Z", "content": "Great job!
", "rawMarkdown": "Great job!" }, { "id": 547828, "postDate": "2019-06-08T11:04:44.323Z", "content": "Congratulations everyone !!! Looking forward for a peek into winning solutions.
", "rawMarkdown": "Congratulations everyone !!! Looking forward for a peek into winning solutions." }, { "id": 618246, "postDate": "2019-09-05T03:22:50.077Z", "rawMarkdown": "", "isDeleted": true } ], "comments": [ { "id": 544720, "author_name": "Mycroft Holmes", "author_url": "", "post_date": "2019-06-05T20:06:25.523000", "content": "A quick suggestion. Kaggle should have the following statement that each sponsor must endorse prior to the competition: \"To the best of our knowledge, Test set has never been released to the public in any shape or form.\"
", "votes": 14, "replies": [] }, { "id": 546310, "author_name": "Scirpus", "author_url": "", "post_date": "2019-06-06T13:08:56.473000", "content": "Thankyou, I enjoyed the competition but I find the 100% positive spin you have put on this is almost Trumpian IMHO. Kaggle hasn't addressed or rebutted a single criticism in the discussions section which is bad form.
\n\nhttps://www.kaggle.com/c/LANL-Earthquake-Prediction/discussion/94411
\n\nMFCC with/without filtering seemed one of the best angles of attack so perhaps after they have researched it they can give us 100s of complete earthquakes using this method as the data would be quite small. Perhaps adding a transverse sensor rather than the single one they use now might also be useful.
", "votes": 4, "replies": [ { "id": 546391, "author_name": "inversion", "author_url": "", "post_date": "2019-06-06T14:38:04.917000", "content": "Hey @Scriptus -
\n\nI don't think you're being very charitable here. We work very hard balancing our time launching new competitions vs addressing all possible concerns. There are approximately 10,000x more active Kagglers than there are Kaggle Data Scientists, which necessitates some degree of balance.
\n\nNearly all competitions have opportunities for improvement identified after thousands of data scientists have spent months scrutinizing them. We always review and try to improve. We don't though, always have the bandwidth to respond to every comment or concern.
\n\nOne reason I haven't responded to the thread you posted - the #4 point in the OP was caused by switching the metric for competition after the kernel submission (which happened pre-launch). The tag didn't update after the fact, even when the Kernel was re-run. This is a submitted bug, but very low priority since this edge case almost never happens. When someone adds that to a long list of concerns and calls it sloppy, I tend to think the comment was more venting than a good-faith effort to improve things, and those discussions generally aren't time well spent.
", "votes": 2, "replies": [] }, { "id": 546408, "author_name": "Scirpus", "author_url": "", "post_date": "2019-06-06T14:55:25.883000", "content": "Hi @inversion - we all appreciate the work you do (even though it might not seem so sometimes). The main point for me at least is that answers to questions completely dried up months ago which seems daft considering the length of the competition.
\n\nMost of us give feedback not to moan but to make Kaggle better - it benefits us all in the end.
", "votes": 6, "replies": [] }, { "id": 546412, "author_name": "inversion", "author_url": "", "post_date": "2019-06-06T15:04:43.113000", "content": "@scirpus I agree with you. This was an unusually long competition, and you are totally right in that engagement dropped off during the second half. This is not ideal at all, and in fact, I took this back to the team as a \"we can do better\" item this past Tuesday.
\n\nI'm be OOO for a few days starting this afternoon, but will get back to these main points next week.
", "votes": 3, "replies": [] }, { "id": 546445, "author_name": "Scirpus", "author_url": "", "post_date": "2019-06-06T15:37:33.113000", "content": "Thanks for the response. I have always appreciated your contributions to Kaggle - not just as an employee of Kaggle but also when you were on the other side of the fence.
", "votes": 1, "replies": [] }, { "id": 546582, "author_name": "inversion", "author_url": "", "post_date": "2019-06-06T17:41:53.733000", "content": "@scirpus Likewise!
", "votes": 1, "replies": [] } ] }, { "id": 550499, "author_name": "Marcel Castro", "author_url": "", "post_date": "2019-06-11T17:15:30.940000", "content": "Congratulation to the winners!!!
", "votes": 1, "replies": [] }, { "id": 546058, "author_name": "Brun", "author_url": "", "post_date": "2019-06-06T07:59:37.057000", "content": "Congratulations to all participants!
", "votes": 1, "replies": [] }, { "id": 2457484, "author_name": "Justin Haire", "author_url": "", "post_date": "2023-09-27T00:57:55.517000", "content": "Great job!
", "votes": 0, "replies": [] }, { "id": 547828, "author_name": "Munish Kaushik", "author_url": "", "post_date": "2019-06-08T11:04:44.323000", "content": "Congratulations everyone !!! Looking forward for a peek into winning solutions.
", "votes": 0, "replies": [] }, { "id": 618246, "author_name": "", "author_url": "", "post_date": "2019-09-05T03:22:50.077000", "content": "", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "544720": "A quick suggestion. Kaggle should have the following statement that each sponsor must endorse prior to the competition: \"To the best of our knowledge, Test set has never been released to the public in any shape or form.\"", "544697": "Thank you all for your hard work in this competition and congratulations to our winners! We know this competition had a shakeup at the end, which keeps things exciting at the end, as well as reinforcing the adage some of you have also mentioned \"Trust the CV.\"\n\nAnd a continued congratulation to the many of you may reach a new tier because of this competition, as well as far more of you for which this was your first competitions.\n\nWe're also continually pleased to see how Kaggle Competitions serve as a great medium and vehicle through which the greater data science community can learn and develop their machine learning abilities and skills. Beginners and experts can come together to start, grow, and succeed. And thanks to the many of you who have shared your solutions in the forums for others to learn from.\n\nWe also would like to give special thanks to Bertrand from LANL, Laura from Purdue, and additional hosts from Penn State and the DoE for allowing us to run this competition. We hope to be able to work with them in the future.\n\nWe've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, please contact [compliance][1]. Please fill in all the fields honestly.\n\nThe top potential winning teams have been contacted via email to provide their winning solutions for sponsor review. Should we need to move down the leaderboard for any reason, we will do so and continue to make contact with subsequent teams.\n\nYou should see your points and medals awarded soon, however it may take a few hours to propagate through.\n\nWe hope to see you in our next competitions!\n\nHappy Modeling!\n\n [1]: https://www.kaggle.com/compliance", "546310": "Thankyou, I enjoyed the competition but I find the 100% positive spin you have put on this is almost Trumpian IMHO. Kaggle hasn't addressed or rebutted a single criticism in the discussions section which is bad form. \n\nhttps://www.kaggle.com/c/LANL-Earthquake-Prediction/discussion/94411\n\nMFCC with/without filtering seemed one of the best angles of attack so perhaps after they have researched it they can give us 100s of complete earthquakes using this method as the data would be quite small. Perhaps adding a transverse sensor rather than the single one they use now might also be useful.\n", "550499": "Congratulation to the winners!!!", "546058": "Congratulations to all participants!", "2457484": "Great job!", "547828": "Congratulations everyone !!! Looking forward for a peek into winning solutions.", "618246": "" } }