{ "id": 403759, "title": "Recap of Competition - Congratulations to the Winners!", "url": "/competitions/icecube-neutrinos-in-deep-ice/discussion/403759", "author_name": "", "post_date": "2023-04-24T17:43:24.699731700Z", "votes": 10, "comment_count": 7, "views": 0, "content": "

Hi Kagglers,

\n

We’re happy to announce the conclusion of the IceCube - Neutrinos in Deep Ice competition. Thank you everyone for your participation!

\n

This competition ended with 6,460 registrations and 901 participants on 812 teams. We had 11,206 submissions from 74 countries. For 100 users (including 9 in the top 100!), this was their first competition. We also had 4 new GrandMasters and 6 new Masters at the conclusion of the competition! Thank you all for your hard work in this competition and congratulations to our winners and to those who gained a new ranking!

\n

The top potential winning teams have been contacted via email for the next steps. We look forward to learning more about their winning solutions.

\n

Here is a curated list of your work. Should you be looking for takeaways in the future, you have a place to see what surfaced from the work performed.

\n

Happy Modeling!
\nKaggle Team

\n

Solution Writeups

\n

You may find the solution writeups here under the “Solution” column.

\n

Top Notebooks (With >50 Votes)

\n

🧊NDI – Let's Learn Together – ELI5 and EDA
\ngraphnet_baseline_submission
\n⚡🧊⚡[LB 1.183] Lightning Fast Baseline with Polars
\nTensorflow LSTM Model Inference
\n3 LSTMs; with Data Picking and Shifting
\ngraphnet_example
\nTensorflow LSTM Model Training TPU
\nIceCube: EDA+PCA baseline CV 1.28 LB 1.274
\nEarly Sharing Prize - DynEdge - 1.046
\n❄️IceCube Neutrinos - Domain & EDA for DS folks
\nMean Angular Error
\nIceCube🧊: Neutrino🎆EDA & 3D🔭interactive viewer
\nAnimated events with matplotlib
\nIceCube🧊: Neutrino Path Least Squares

\n

Other Top Discussions (With >35 Votes)

\n

Welcome to the challenge!
\n2nd place solution: Neutrino direction prediction with transformers
\nGraphNeT: DynEdge Baseline & Example
\nNeutrino Events Visualized
\nAnimated events with matplotlib
\n3rd Place - Attention + XGBoost Ensembler
\n1st Place Solution
\nDomain information - neutrino, anti-neutrino and spins
\nDerivation of Line-fit least squares
\nThe logic used for 'auxiliary' column True vs False
\n∞ Explanation and Improvement von Mises-Fisher Loss
\nHere are some open-source code or resources specifically related to neutrino direction prediction.
\n11-th place solution: Attention, GNN, Ensemble

", "messages": [ { "id": "2232926", "postDate": "04/24/2023 17:43:24", "content": "

Hi Kagglers,

\n

We’re happy to announce the conclusion of the IceCube - Neutrinos in Deep Ice competition. Thank you everyone for your participation!

\n

This competition ended with 6,460 registrations and 901 participants on 812 teams. We had 11,206 submissions from 74 countries. For 100 users (including 9 in the top 100!), this was their first competition. We also had 4 new GrandMasters and 6 new Masters at the conclusion of the competition! Thank you all for your hard work in this competition and congratulations to our winners and to those who gained a new ranking!

\n

The top potential winning teams have been contacted via email for the next steps. We look forward to learning more about their winning solutions.

\n

Here is a curated list of your work. Should you be looking for takeaways in the future, you have a place to see what surfaced from the work performed.

\n

Happy Modeling!
\nKaggle Team

\n

Solution Writeups

\n

You may find the solution writeups here under the “Solution” column.

\n

Top Notebooks (With >50 Votes)

\n

🧊NDI – Let's Learn Together – ELI5 and EDA
\ngraphnet_baseline_submission
\n⚡🧊⚡[LB 1.183] Lightning Fast Baseline with Polars
\nTensorflow LSTM Model Inference
\n3 LSTMs; with Data Picking and Shifting
\ngraphnet_example
\nTensorflow LSTM Model Training TPU
\nIceCube: EDA+PCA baseline CV 1.28 LB 1.274
\nEarly Sharing Prize - DynEdge - 1.046
\n❄️IceCube Neutrinos - Domain & EDA for DS folks
\nMean Angular Error
\nIceCube🧊: Neutrino🎆EDA & 3D🔭interactive viewer
\nAnimated events with matplotlib
\nIceCube🧊: Neutrino Path Least Squares

\n

Other Top Discussions (With >35 Votes)

\n

Welcome to the challenge!
\n2nd place solution: Neutrino direction prediction with transformers
\nGraphNeT: DynEdge Baseline & Example
\nNeutrino Events Visualized
\nAnimated events with matplotlib
\n3rd Place - Attention + XGBoost Ensembler
\n1st Place Solution
\nDomain information - neutrino, anti-neutrino and spins
\nDerivation of Line-fit least squares
\nThe logic used for 'auxiliary' column True vs False
\n∞ Explanation and Improvement von Mises-Fisher Loss
\nHere are some open-source code or resources specifically related to neutrino direction prediction.
\n11-th place solution: Attention, GNN, Ensemble

", "rawMarkdown": "Hi Kagglers,\n\nWe’re happy to announce the conclusion of the IceCube - Neutrinos in Deep Ice competition. Thank you everyone for your participation!\n\nThis competition ended with 6,460 registrations and 901 participants on 812 teams. We had 11,206 submissions from 74 countries. For 100 users (including 9 in the top 100!), this was their first competition. We also had 4 new GrandMasters and 6 new Masters at the conclusion of the competition! Thank you all for your hard work in this competition and congratulations to our winners and to those who gained a new ranking! \n\nThe top potential winning teams have been contacted via email for the next steps. We look forward to learning more about their winning solutions.\n\nHere is a curated list of your work. Should you be looking for takeaways in the future, you have a place to see what surfaced from the work performed.\n\nHappy Modeling!\nKaggle Team\n\n##Solution Writeups\nYou may find the solution writeups [here](https://www.kaggle.com/competitions/icecube-neutrinos-in-deep-ice/leaderboard) under the “Solution” column.\n\n##Top Notebooks (With >50 Votes)\n[🧊NDI – Let's Learn Together – ELI5 and EDA](https://kaggle.com/code/dschettler8845/ndi-let-s-learn-together-eli5-and-eda)\n[graphnet_baseline_submission](https://kaggle.com/code/rasmusrse/graphnet-baseline-submission)\n[⚡🧊⚡[LB 1.183] Lightning Fast Baseline with Polars](https://kaggle.com/code/roberthatch/lb-1-183-lightning-fast-baseline-with-polars)\n[Tensorflow LSTM Model Inference](https://kaggle.com/code/rsmits/tensorflow-lstm-model-inference)\n[3 LSTMs; with Data Picking and Shifting](https://kaggle.com/code/seungmoklee/3-lstms-with-data-picking-and-shifting)\n[graphnet_example](https://kaggle.com/code/rasmusrse/graphnet-example)\n[Tensorflow LSTM Model Training TPU](https://kaggle.com/code/rsmits/tensorflow-lstm-model-training-tpu)\n[IceCube: EDA+PCA baseline CV 1.28 LB 1.274](https://kaggle.com/code/shlomoron/icecube-eda-pca-baseline-cv-1-23-lb-1-218)\n[Early Sharing Prize - DynEdge - 1.046](https://kaggle.com/code/anjum48/early-sharing-prize-dynedge-1-046)\n[❄️IceCube Neutrinos - Domain & EDA for DS folks](https://kaggle.com/code/mvvppp/icecube-neutrinos-domain-eda-for-ds-folks)\n[Mean Angular Error](https://kaggle.com/code/sohier/mean-angular-error)\n[IceCube🧊: Neutrino🎆EDA & 3D🔭interactive viewer](https://kaggle.com/code/jirkaborovec/icecube-neutrino-eda-3d-interactive-viewer)\n[Animated events with matplotlib](https://kaggle.com/code/pestipeti/animated-events-with-matplotlib)\n[IceCube🧊: Neutrino Path Least Squares](https://kaggle.com/code/solverworld/icecube-neutrino-path-least-squares-1-214)\n\n##Other Top Discussions (With >35 Votes)\n[Welcome to the challenge!](https://kaggle.com/c/38257/discussion/355653)\n[2nd place solution: Neutrino direction prediction with transformers](https://kaggle.com/c/38257/discussion/402882)\n[GraphNeT: DynEdge Baseline & Example](https://kaggle.com/c/38257/discussion/383524)\n[Neutrino Events Visualized](https://kaggle.com/c/38257/discussion/381166)\n[Animated events with matplotlib](https://kaggle.com/c/38257/discussion/381935)\n[3rd Place - Attention + XGBoost Ensembler](https://kaggle.com/c/38257/discussion/402888)\n[1st Place Solution](https://kaggle.com/c/38257/discussion/402976)\n[Domain information - neutrino, anti-neutrino and spins](https://kaggle.com/c/38257/discussion/379546)\n[Derivation of Line-fit least squares ](https://kaggle.com/c/38257/discussion/381747)\n[The logic used for 'auxiliary' column True vs False](https://kaggle.com/c/38257/discussion/379677)\n[∞ Explanation and Improvement von Mises-Fisher Loss](https://kaggle.com/c/38257/discussion/392096)\n[Here are some open-source code or resources specifically related to neutrino direction prediction.](https://kaggle.com/c/38257/discussion/379882)\n[11-th place solution: Attention, GNN, Ensemble](https://kaggle.com/c/38257/discussion/402920)", "votes": null }, { "id": "2234003", "postDate": "04/24/2023 19:03:04", "content": "

@ashleychow Congratulations to the Winners! And thank you for many interesting and helpful links in one place!

", "rawMarkdown": "ashleychow Congratulations to the Winners! And thank you for many interesting and helpful links in one place!", "votes": null }, { "id": "2236177", "postDate": "04/26/2023 15:46:33", "content": "

Can you add this link for the 12th place solution:
\n12th place solution

", "rawMarkdown": "Can you add this link for the 12th place solution:\n[12th place solution](https://www.kaggle.com/competitions/icecube-neutrinos-in-deep-ice/discussion/403000)", "votes": null }, { "id": "2236553", "postDate": "04/27/2023 01:07:09", "content": "

Thanks @solverworld! Let me check why this is not reflected there. Thanks for flagging!

", "rawMarkdown": "Thanks @solverworld! Let me check why this is not reflected there. Thanks for flagging!", "votes": null }, { "id": "2236635", "postDate": "04/27/2023 02:35:22", "content": "

Hi @solverworld, just checking - did you get to follow the instructions outlined here? Thanks!

", "rawMarkdown": "Hi @solverworld, just checking - did you get to follow the instructions outlined [here](https://www.kaggle.com/product-feedback/373153)? Thanks!", "votes": null }, { "id": "2237107", "postDate": "04/27/2023 11:30:05", "content": "

No, I did not know about that. But done now and it works. Thanks

", "rawMarkdown": "No, I did not know about that. But done now and it works. Thanks", "votes": null }, { "id": "2237158", "postDate": "04/27/2023 12:17:56", "content": "

Congratulations!!

", "rawMarkdown": "Congratulations!!", "votes": null }, { "id": "2237670", "postDate": "04/27/2023 20:50:21", "content": "

Great! Thanks @solverworld!!

", "rawMarkdown": "Great! Thanks @solverworld!!", "votes": null } ], "comments": [ { "id": 2234003, "author_name": "serangu", "author_url": "", "post_date": "04/24/2023 19:03:04", "content": "

@ashleychow Congratulations to the Winners! And thank you for many interesting and helpful links in one place!

", "votes": null, "replies": [] }, { "id": 2236177, "author_name": "solverworld", "author_url": "", "post_date": "04/26/2023 15:46:33", "content": "

Can you add this link for the 12th place solution:
\n12th place solution

", "votes": null, "replies": [ { "id": 2236553, "author_name": "ashleychow", "author_url": "", "post_date": "04/27/2023 01:07:09", "content": "

Thanks @solverworld! Let me check why this is not reflected there. Thanks for flagging!

", "votes": null, "replies": [ { "id": 2236635, "author_name": "ashleychow", "author_url": "", "post_date": "04/27/2023 02:35:22", "content": "

Hi @solverworld, just checking - did you get to follow the instructions outlined here? Thanks!

", "votes": null, "replies": [ { "id": 2237107, "author_name": "solverworld", "author_url": "", "post_date": "04/27/2023 11:30:05", "content": "

No, I did not know about that. But done now and it works. Thanks

", "votes": null, "replies": [ { "id": 2237670, "author_name": "ashleychow", "author_url": "", "post_date": "04/27/2023 20:50:21", "content": "

Great! Thanks @solverworld!!

", "votes": null, "replies": [] } ] } ] } ] } ] }, { "id": 2237158, "author_name": "ariunabanzarkhanova", "author_url": "", "post_date": "04/27/2023 12:17:56", "content": "

Congratulations!!

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "2232926": "Hi Kagglers,\n\nWe’re happy to announce the conclusion of the IceCube - Neutrinos in Deep Ice competition. Thank you everyone for your participation!\n\nThis competition ended with 6,460 registrations and 901 participants on 812 teams. We had 11,206 submissions from 74 countries. For 100 users (including 9 in the top 100!), this was their first competition. We also had 4 new GrandMasters and 6 new Masters at the conclusion of the competition! Thank you all for your hard work in this competition and congratulations to our winners and to those who gained a new ranking! \n\nThe top potential winning teams have been contacted via email for the next steps. We look forward to learning more about their winning solutions.\n\nHere is a curated list of your work. Should you be looking for takeaways in the future, you have a place to see what surfaced from the work performed.\n\nHappy Modeling!\nKaggle Team\n\n##Solution Writeups\nYou may find the solution writeups [here](https://www.kaggle.com/competitions/icecube-neutrinos-in-deep-ice/leaderboard) under the “Solution” column.\n\n##Top Notebooks (With >50 Votes)\n[🧊NDI – Let's Learn Together – ELI5 and EDA](https://kaggle.com/code/dschettler8845/ndi-let-s-learn-together-eli5-and-eda)\n[graphnet_baseline_submission](https://kaggle.com/code/rasmusrse/graphnet-baseline-submission)\n[⚡🧊⚡[LB 1.183] Lightning Fast Baseline with Polars](https://kaggle.com/code/roberthatch/lb-1-183-lightning-fast-baseline-with-polars)\n[Tensorflow LSTM Model Inference](https://kaggle.com/code/rsmits/tensorflow-lstm-model-inference)\n[3 LSTMs; with Data Picking and Shifting](https://kaggle.com/code/seungmoklee/3-lstms-with-data-picking-and-shifting)\n[graphnet_example](https://kaggle.com/code/rasmusrse/graphnet-example)\n[Tensorflow LSTM Model Training TPU](https://kaggle.com/code/rsmits/tensorflow-lstm-model-training-tpu)\n[IceCube: EDA+PCA baseline CV 1.28 LB 1.274](https://kaggle.com/code/shlomoron/icecube-eda-pca-baseline-cv-1-23-lb-1-218)\n[Early Sharing Prize - DynEdge - 1.046](https://kaggle.com/code/anjum48/early-sharing-prize-dynedge-1-046)\n[❄️IceCube Neutrinos - Domain & EDA for DS folks](https://kaggle.com/code/mvvppp/icecube-neutrinos-domain-eda-for-ds-folks)\n[Mean Angular Error](https://kaggle.com/code/sohier/mean-angular-error)\n[IceCube🧊: Neutrino🎆EDA & 3D🔭interactive viewer](https://kaggle.com/code/jirkaborovec/icecube-neutrino-eda-3d-interactive-viewer)\n[Animated events with matplotlib](https://kaggle.com/code/pestipeti/animated-events-with-matplotlib)\n[IceCube🧊: Neutrino Path Least Squares](https://kaggle.com/code/solverworld/icecube-neutrino-path-least-squares-1-214)\n\n##Other Top Discussions (With >35 Votes)\n[Welcome to the challenge!](https://kaggle.com/c/38257/discussion/355653)\n[2nd place solution: Neutrino direction prediction with transformers](https://kaggle.com/c/38257/discussion/402882)\n[GraphNeT: DynEdge Baseline & Example](https://kaggle.com/c/38257/discussion/383524)\n[Neutrino Events Visualized](https://kaggle.com/c/38257/discussion/381166)\n[Animated events with matplotlib](https://kaggle.com/c/38257/discussion/381935)\n[3rd Place - Attention + XGBoost Ensembler](https://kaggle.com/c/38257/discussion/402888)\n[1st Place Solution](https://kaggle.com/c/38257/discussion/402976)\n[Domain information - neutrino, anti-neutrino and spins](https://kaggle.com/c/38257/discussion/379546)\n[Derivation of Line-fit least squares ](https://kaggle.com/c/38257/discussion/381747)\n[The logic used for 'auxiliary' column True vs False](https://kaggle.com/c/38257/discussion/379677)\n[∞ Explanation and Improvement von Mises-Fisher Loss](https://kaggle.com/c/38257/discussion/392096)\n[Here are some open-source code or resources specifically related to neutrino direction prediction.](https://kaggle.com/c/38257/discussion/379882)\n[11-th place solution: Attention, GNN, Ensemble](https://kaggle.com/c/38257/discussion/402920)", "2234003": "ashleychow Congratulations to the Winners! And thank you for many interesting and helpful links in one place!", "2236177": "Can you add this link for the 12th place solution:\n[12th place solution](https://www.kaggle.com/competitions/icecube-neutrinos-in-deep-ice/discussion/403000)", "2236553": "Thanks @solverworld! Let me check why this is not reflected there. Thanks for flagging!", "2236635": "Hi @solverworld, just checking - did you get to follow the instructions outlined [here](https://www.kaggle.com/product-feedback/373153)? Thanks!", "2237107": "No, I did not know about that. But done now and it works. Thanks", "2237158": "Congratulations!!", "2237670": "Great! Thanks @solverworld!!" }, "source": "meta" }