\n
![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F17484946%2F716c5b04f39695bfd1a3fe324734aa73%2F1.png?generation=1750829178293377&alt=media\")
\n
![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F17484946%2F3aa25c4d76ee3da6dabd532b42b2eb1b%2F2.png?generation=1750829193976281&alt=media\")
\n
![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F17484946%2F316d41dba444839e1d236ca3020b687a%2F3.png?generation=1750829205058827&alt=media\")
Here, I would like to remind the organizers not to forget to deal with suspected cheating in this competition. The time series competition is scored based on real data, and the rankings are generally finalized and announced directly in the last round, so it is strongly recommended that Kaggle check it carefully.
\nWe can see that some users have joined Kaggle for less than a month, but they are not active.
\nLook how many negative votes I will get π
\nThis is an example of a suspicious area.
\n
\n
\n
Checking the activity records of some accounts, we can see that:
\nSome accounts have no active records for a long time, but suddenly come online and submit predictions during the competition;
\nThese accounts have consistent active cycles and contribution graphs.
\nThese signs are highly consistent with the strategy of \"controlling multiple accounts to participate in the competition together and trying to submit multiple results to test the leaderboard.\"
\n![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F17484946%2Faaa2855585b85e272776ee738358dcfd%2F5.png?generation=1750829244349315&alt=media\")
\n![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F17484946%2Faa2ea153a7a28a7a0ca55c54186a7cd3%2F6.png?generation=1750829267536275&alt=media\")
\n![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F17484946%2Fb4a48c03786b32f0b8c931b5c61d8bbb%2F7.png?generation=1750829275964778&alt=media\")
\n![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F17484946%2F2d8e5bc1711ae279642be9d9724e8bf5%2F8.png?generation=1750829285171540&alt=media\")
\n![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F17484946%2Fc539781c9a62193f426b575dc6bf03b1%2F9.png?generation=1750829293442316&alt=media\")
I suggest checking whether the source of their forked open source notebook is the same, whether the same changes can improve the score.
\nAnother strong suggestion is to track whether the email address of the winning account has changed, activity, etc. after the medal is issued.
@ryanholbrook @kaitoneil @mylesoneill @mdesaijs @maggiemd @wcukierski @addisonhoward
", "messages": [ { "id": "3231893", "postDate": "06/25/2025 05:31:38", "content": "Here, I would like to remind the organizers not to forget to deal with suspected cheating in this competition. The time series competition is scored based on real data, and the rankings are generally finalized and announced directly in the last round, so it is strongly recommended that Kaggle check it carefully.
\nWe can see that some users have joined Kaggle for less than a month, but they are not active.
\nLook how many negative votes I will get π
\nThis is an example of a suspicious area.
\n
\n
\n
Checking the activity records of some accounts, we can see that:
\nSome accounts have no active records for a long time, but suddenly come online and submit predictions during the competition;
\nThese accounts have consistent active cycles and contribution graphs.
\nThese signs are highly consistent with the strategy of \"controlling multiple accounts to participate in the competition together and trying to submit multiple results to test the leaderboard.\"
\n
\n
\n
\n
\n
I suggest checking whether the source of their forked open source notebook is the same, whether the same changes can improve the score.
\nAnother strong suggestion is to track whether the email address of the winning account has changed, activity, etc. after the medal is issued.
@ryanholbrook @kaitoneil @mylesoneill @mdesaijs @maggiemd @wcukierski @addisonhoward
", "rawMarkdown": "Here, I would like to remind the organizers not to forget to deal with suspected cheating in this competition. The time series competition is scored based on real data, and the rankings are generally finalized and announced directly in the last round, so it is strongly recommended that Kaggle check it carefully.\n\nWe can see that some users have joined Kaggle for less than a month, but they are not active.\n\nLook how many negative votes I will get π \n\nThis is an example of a suspicious area.\n\n\n\n\nChecking the activity records of some accounts, we can see that:\n\nSome accounts have no active records for a long time, but suddenly come online and submit predictions during the competition;\n\nThese accounts have consistent active cycles and contribution graphs.\n\nThese signs are highly consistent with the strategy of \"controlling multiple accounts to participate in the competition together and trying to submit multiple results to test the leaderboard.\"\n\n\n\n\n\n\nI suggest checking whether the source of their forked open source notebook is the same, whether the same changes can improve the score.\nAnother strong suggestion is to track whether the email address of the winning account has changed, activity, etc. after the medal is issued.\n\n@ryanholbrook @kaitoneil @mylesoneill @mdesaijs @maggiemd @wcukierski @addisonhoward", "votes": null }, { "id": "3232637", "postDate": "06/26/2025 03:26:52", "content": "I'm curious, why there are downvotes?
", "rawMarkdown": "I'm curious, why there are downvotes?", "votes": null }, { "id": "3234589", "postDate": "06/28/2025 05:11:58", "content": "You threatened them.π
", "rawMarkdown": "You threatened them.π", "votes": null }, { "id": "3235435", "postDate": "06/29/2025 08:40:30", "content": "@wayne127 Itβs amazing to be able to turn Kaggle into a business
", "rawMarkdown": "wayne127 Itβs amazing to be able to turn Kaggle into a business", "votes": null }, { "id": "3240702", "postDate": "07/04/2025 06:13:07", "content": "sad to see this happening on kaggle
", "rawMarkdown": "sad to see this happening on kaggle", "votes": null }, { "id": "3242497", "postDate": "07/06/2025 01:09:57", "content": "@yourxamit Nearly 80 to 90 teams are suspected of having problems, almost 400 people, it's too much.
", "rawMarkdown": "yourxamit Nearly 80 to 90 teams are suspected of having problems, almost 400 people, it's too much.", "votes": null }, { "id": "3242600", "postDate": "07/06/2025 06:04:38", "content": "Unfortunately, this has been a problem on other competitions as well :(. I just try to ignore it, I'm here to learn more than anything else.
", "rawMarkdown": "Unfortunately, this has been a problem on other competitions as well :(. I just try to ignore it, I'm here to learn more than anything else.", "votes": null }, { "id": "3243414", "postDate": "07/07/2025 05:54:47", "content": "@taylorsamarel Kaggle is really good. I only knew about the data sets before, but now the competitions in Kaggle are really excellent. They are all following the cutting-edge directions, such as solving Olympic questions with large models and ARC competitions. It is also the best way to learn new fields. I even learned about NLP subdivisions in Kaggle, such as NER, text classification, quantification, power time series and other directional knowledge. But because of its excellence, there are so many cheaters in Kaggle. I am a little speechless. This will greatly reduce the status of Kaggle. There are too many opportunistic people. Kaggle's anti-cheating is also quite good, but it still can't stand these cheaters.
", "rawMarkdown": "taylorsamarel Kaggle is really good. I only knew about the data sets before, but now the competitions in Kaggle are really excellent. They are all following the cutting-edge directions, such as solving Olympic questions with large models and ARC competitions. It is also the best way to learn new fields. I even learned about NLP subdivisions in Kaggle, such as NER, text classification, quantification, power time series and other directional knowledge. But because of its excellence, there are so many cheaters in Kaggle. I am a little speechless. This will greatly reduce the status of Kaggle. There are too many opportunistic people. Kaggle's anti-cheating is also quite good, but it still can't stand these cheaters.", "votes": null }, { "id": "3246980", "postDate": "07/11/2025 22:42:05", "content": "But the thing is kaggle has verification step before me join any competition, so how a person can verify multiple accounts?
", "rawMarkdown": "But the thing is kaggle has verification step before me join any competition, so how a person can verify multiple accounts?", "votes": null } ], "comments": [ { "id": 3232637, "author_name": "oralia", "author_url": "", "post_date": "06/26/2025 03:26:52", "content": "I'm curious, why there are downvotes?
", "votes": null, "replies": [ { "id": 3234589, "author_name": "wayne127", "author_url": "", "post_date": "06/28/2025 05:11:58", "content": "You threatened them.π
", "votes": null, "replies": [ { "id": 3235435, "author_name": "oralia", "author_url": "", "post_date": "06/29/2025 08:40:30", "content": "@wayne127 Itβs amazing to be able to turn Kaggle into a business
", "votes": null, "replies": [] } ] } ] }, { "id": 3240702, "author_name": "yourxamit", "author_url": "", "post_date": "07/04/2025 06:13:07", "content": "sad to see this happening on kaggle
", "votes": null, "replies": [ { "id": 3242497, "author_name": "oralia", "author_url": "", "post_date": "07/06/2025 01:09:57", "content": "@yourxamit Nearly 80 to 90 teams are suspected of having problems, almost 400 people, it's too much.
", "votes": null, "replies": [] } ] }, { "id": 3242600, "author_name": "taylorsamarel", "author_url": "", "post_date": "07/06/2025 06:04:38", "content": "Unfortunately, this has been a problem on other competitions as well :(. I just try to ignore it, I'm here to learn more than anything else.
", "votes": null, "replies": [ { "id": 3243414, "author_name": "oralia", "author_url": "", "post_date": "07/07/2025 05:54:47", "content": "@taylorsamarel Kaggle is really good. I only knew about the data sets before, but now the competitions in Kaggle are really excellent. They are all following the cutting-edge directions, such as solving Olympic questions with large models and ARC competitions. It is also the best way to learn new fields. I even learned about NLP subdivisions in Kaggle, such as NER, text classification, quantification, power time series and other directional knowledge. But because of its excellence, there are so many cheaters in Kaggle. I am a little speechless. This will greatly reduce the status of Kaggle. There are too many opportunistic people. Kaggle's anti-cheating is also quite good, but it still can't stand these cheaters.
", "votes": null, "replies": [] } ] }, { "id": 3246980, "author_name": "sheemamasood", "author_url": "", "post_date": "07/11/2025 22:42:05", "content": "But the thing is kaggle has verification step before me join any competition, so how a person can verify multiple accounts?
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "3231893": "Here, I would like to remind the organizers not to forget to deal with suspected cheating in this competition. The time series competition is scored based on real data, and the rankings are generally finalized and announced directly in the last round, so it is strongly recommended that Kaggle check it carefully.\n\nWe can see that some users have joined Kaggle for less than a month, but they are not active.\n\nLook how many negative votes I will get π \n\nThis is an example of a suspicious area.\n\n\n\n\nChecking the activity records of some accounts, we can see that:\n\nSome accounts have no active records for a long time, but suddenly come online and submit predictions during the competition;\n\nThese accounts have consistent active cycles and contribution graphs.\n\nThese signs are highly consistent with the strategy of \"controlling multiple accounts to participate in the competition together and trying to submit multiple results to test the leaderboard.\"\n\n\n\n\n\n\nI suggest checking whether the source of their forked open source notebook is the same, whether the same changes can improve the score.\nAnother strong suggestion is to track whether the email address of the winning account has changed, activity, etc. after the medal is issued.\n\n@ryanholbrook @kaitoneil @mylesoneill @mdesaijs @maggiemd @wcukierski @addisonhoward", "3232637": "I'm curious, why there are downvotes?", "3234589": "You threatened them.π", "3235435": "wayne127 Itβs amazing to be able to turn Kaggle into a business", "3240702": "sad to see this happening on kaggle", "3242497": "yourxamit Nearly 80 to 90 teams are suspected of having problems, almost 400 people, it's too much.", "3242600": "Unfortunately, this has been a problem on other competitions as well :(. I just try to ignore it, I'm here to learn more than anything else.", "3243414": "taylorsamarel Kaggle is really good. I only knew about the data sets before, but now the competitions in Kaggle are really excellent. They are all following the cutting-edge directions, such as solving Olympic questions with large models and ARC competitions. It is also the best way to learn new fields. I even learned about NLP subdivisions in Kaggle, such as NER, text classification, quantification, power time series and other directional knowledge. But because of its excellence, there are so many cheaters in Kaggle. I am a little speechless. This will greatly reduce the status of Kaggle. There are too many opportunistic people. Kaggle's anti-cheating is also quite good, but it still can't stand these cheaters.", "3246980": "But the thing is kaggle has verification step before me join any competition, so how a person can verify multiple accounts?" }, "source": "meta" }