Hey Kagglers,
\n\nThe ASHRAE Great Energy Predictor competition has closed! We hope you were able to learn a lot, and use your machine learning skills on this interesting problem. As noted in (a number of) other posts, the closing process for this competition took an unexpected turn, so we certainly appreciate your patience as we worked out the final details.
\n\nWe had year had 4,370 participants on 3614 teams with over 39,403 submissions from 94 countries! For 948 users (including the 8th place finishers!, and 32 individuals in the Top 100), this was their first competition. We also had 87 new Masters or Experts at the conclusion of this 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\nAn extended congratulations to Patrick0302 who ended on top of the leaderboard on the replica of the 1993 competition!
\n\nWe were excited to work with all the folks at ASHRAE, PSD Consulting, SinBerBEST, BUDS Lab, and Texas A&M, like Chris Balbach, Clayton Miller, Krishnan Kowri, and Jeff Haberl. We're glad they choose Kaggle to be a platform to bring these types of problems to the broader data science community. They've been a pleasure to work with, and we hope to work with them again in the future. Be sure to check out the work they put together at the ASHRAE Winter and Annual meetings this year.
\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. Further, in this competition, many can use their machine learning skills to help a great cause like this one.
\n\nWe've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, or believe you have evidence that suggests another team cheated, 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 host 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 have already seen your points and medals awarded, however it may take a few hours to propagate through if yours are still missing.
\n\nIn the meantime, I've created this thread to be a curated list of your work. As you post your solutions, top kernels, and general discussion posts, I'll update this thread to keep track. If you write a paper, thesis, or present at a conference, and would like to share your work - please let us know so we can share with the Kaggle community! Additionally, if you performed any data manipulation, or maybe used a new technique in this competition that you'd like to share to further the industry, please let us know and we'll post it here! That way, should you be looking for takeaways in the future, or if you've just now stumbled across the competition, you have a place to see what surfaced from the work performed.
\n\nHappy Modeling!\nKaggle Team
\n\nHey Kagglers,
\n\nThe ASHRAE Great Energy Predictor competition has closed! We hope you were able to learn a lot, and use your machine learning skills on this interesting problem. As noted in (a number of) other posts, the closing process for this competition took an unexpected turn, so we certainly appreciate your patience as we worked out the final details.
\n\nWe had year had 4,370 participants on 3614 teams with over 39,403 submissions from 94 countries! For 948 users (including the 8th place finishers!, and 32 individuals in the Top 100), this was their first competition. We also had 87 new Masters or Experts at the conclusion of this 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\nAn extended congratulations to Patrick0302 who ended on top of the leaderboard on the replica of the 1993 competition!
\n\nWe were excited to work with all the folks at ASHRAE, PSD Consulting, SinBerBEST, BUDS Lab, and Texas A&M, like Chris Balbach, Clayton Miller, Krishnan Kowri, and Jeff Haberl. We're glad they choose Kaggle to be a platform to bring these types of problems to the broader data science community. They've been a pleasure to work with, and we hope to work with them again in the future. Be sure to check out the work they put together at the ASHRAE Winter and Annual meetings this year.
\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. Further, in this competition, many can use their machine learning skills to help a great cause like this one.
\n\nWe've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, or believe you have evidence that suggests another team cheated, 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 host 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 have already seen your points and medals awarded, however it may take a few hours to propagate through if yours are still missing.
\n\nIn the meantime, I've created this thread to be a curated list of your work. As you post your solutions, top kernels, and general discussion posts, I'll update this thread to keep track. If you write a paper, thesis, or present at a conference, and would like to share your work - please let us know so we can share with the Kaggle community! Additionally, if you performed any data manipulation, or maybe used a new technique in this competition that you'd like to share to further the industry, please let us know and we'll post it here! That way, should you be looking for takeaways in the future, or if you've just now stumbled across the competition, you have a place to see what surfaced from the work performed.
\n\nHappy Modeling!\nKaggle Team
\n\nCongratulations for everyone!
", "rawMarkdown": "Congratulations for everyone!", "votes": null }, { "id": "713488", "postDate": "01/08/2020 10:42:27", "content": "Thank you @sohier and @addisonhoward and the rest of the Kaggle team! And congratulations to the winning teams!\nIt was my first competition and I did learn a lot. I am preparing a repository with my solution and the code I developed to perform data cleaning, which I think might be helpful to others. I will share it here when it is ready.
", "rawMarkdown": "Thank you @sohier and @addisonhoward and the rest of the Kaggle team! And congratulations to the winning teams!\nIt was my first competition and I did learn a lot. I am preparing a repository with my solution and the code I developed to perform data cleaning, which I think might be helpful to others. I will share it here when it is ready.", "votes": null }, { "id": "714776", "postDate": "01/09/2020 18:23:56", "content": "Can ASHRAE kindly publish the «solution» file and the uploaded solution files from say the three best algorithms from public and private LBs? This would be really very useful for research teams to continue and benchmark future algorithms.
", "rawMarkdown": "Can ASHRAE kindly publish the «solution» file and the uploaded solution files from say the three best algorithms from public and private LBs? This would be really very useful for research teams to continue and benchmark future algorithms.", "votes": null }, { "id": "717347", "postDate": "01/13/2020 03:40:50", "content": "Congrats to everyone! We really appreciate everyone's participation in the competition. Thanks for everyone's patience despite the hiccups. We really believe that this competition succeeded in getting the building science and data science communities to understand each other better! I know I learned quite a bit.
\n\nWe are in the process of curating a directory of Notebooks for building performance engineers and analysts from the competition that will serve as a recipe book for beginners as well as experts who are curious to learn about certain topics. We highly encourage you all to share your solutions as a notebook for this purpose. We will acknowledge the authors of all notebooks in this process, so please annotate your notebook or profile with how you would like to be acknowledged. It would also be helpful if you could indicate whether you are an ASHRAE member.
", "rawMarkdown": "Congrats to everyone! We really appreciate everyone's participation in the competition. Thanks for everyone's patience despite the hiccups. We really believe that this competition succeeded in getting the building science and data science communities to understand each other better! I know I learned quite a bit.\n\n**We are in the process of curating a directory of Notebooks for building performance engineers and analysts from the competition that will serve as a recipe book for beginners as well as experts who are curious to learn about certain topics. We highly encourage you all to share your solutions as a notebook for this purpose. We will acknowledge the authors of all notebooks in this process, so please annotate your notebook or profile with how you would like to be acknowledged. It would also be helpful if you could indicate whether you are an ASHRAE member.**", "votes": null }, { "id": "717348", "postDate": "01/13/2020 03:41:41", "content": "yes! We plan to organize and publish as many of the top solutions as possible, including the top 5
", "rawMarkdown": "yes! We plan to organize and publish as many of the top solutions as possible, including the top 5", "votes": null }, { "id": "717349", "postDate": "01/13/2020 03:42:15", "content": "yes! please share :)
", "rawMarkdown": "yes! please share :)", "votes": null }, { "id": "724386", "postDate": "01/21/2020 05:46:16", "content": "congratulation to all....appreciated for their hard work....
", "rawMarkdown": "congratulation to all....appreciated for their hard work....", "votes": null }, { "id": "725556", "postDate": "01/22/2020 08:42:06", "content": "Are you planning to release the test set with ground truth values?
", "rawMarkdown": "Are you planning to release the test set with ground truth values?", "votes": null }, { "id": "727285", "postDate": "01/23/2020 15:53:51", "content": "Is ASHRAE planning to release the complete test set with ground truth values?
", "rawMarkdown": "Is ASHRAE planning to release the complete test set with ground truth values?", "votes": null } ], "comments": [ { "id": 713465, "author_name": "brunhs", "author_url": "", "post_date": "01/08/2020 10:00:58", "content": "Congratulations for everyone!
", "votes": null, "replies": [] }, { "id": 713488, "author_name": "dtavan", "author_url": "", "post_date": "01/08/2020 10:42:27", "content": "Thank you @sohier and @addisonhoward and the rest of the Kaggle team! And congratulations to the winning teams!\nIt was my first competition and I did learn a lot. I am preparing a repository with my solution and the code I developed to perform data cleaning, which I think might be helpful to others. I will share it here when it is ready.
", "votes": null, "replies": [ { "id": 717349, "author_name": "claytonmiller", "author_url": "", "post_date": "01/13/2020 03:42:15", "content": "yes! please share :)
", "votes": null, "replies": [] } ] }, { "id": 714776, "author_name": "petergschild", "author_url": "", "post_date": "01/09/2020 18:23:56", "content": "Can ASHRAE kindly publish the «solution» file and the uploaded solution files from say the three best algorithms from public and private LBs? This would be really very useful for research teams to continue and benchmark future algorithms.
", "votes": null, "replies": [ { "id": 717348, "author_name": "claytonmiller", "author_url": "", "post_date": "01/13/2020 03:41:41", "content": "yes! We plan to organize and publish as many of the top solutions as possible, including the top 5
", "votes": null, "replies": [] }, { "id": 725556, "author_name": "linker", "author_url": "", "post_date": "01/22/2020 08:42:06", "content": "Are you planning to release the test set with ground truth values?
", "votes": null, "replies": [] } ] }, { "id": 717347, "author_name": "claytonmiller", "author_url": "", "post_date": "01/13/2020 03:40:50", "content": "Congrats to everyone! We really appreciate everyone's participation in the competition. Thanks for everyone's patience despite the hiccups. We really believe that this competition succeeded in getting the building science and data science communities to understand each other better! I know I learned quite a bit.
\n\nWe are in the process of curating a directory of Notebooks for building performance engineers and analysts from the competition that will serve as a recipe book for beginners as well as experts who are curious to learn about certain topics. We highly encourage you all to share your solutions as a notebook for this purpose. We will acknowledge the authors of all notebooks in this process, so please annotate your notebook or profile with how you would like to be acknowledged. It would also be helpful if you could indicate whether you are an ASHRAE member.
", "votes": null, "replies": [] }, { "id": 724386, "author_name": "anitaml", "author_url": "", "post_date": "01/21/2020 05:46:16", "content": "congratulation to all....appreciated for their hard work....
", "votes": null, "replies": [] }, { "id": 727285, "author_name": "linker", "author_url": "", "post_date": "01/23/2020 15:53:51", "content": "Is ASHRAE planning to release the complete test set with ground truth values?
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "713293": "Hey Kagglers,\n\nThe ASHRAE Great Energy Predictor competition has closed! We hope you were able to learn a lot, and use your machine learning skills on this interesting problem. As noted in (a number of) other posts, the closing process for this competition took an unexpected turn, so we certainly appreciate your patience as we worked out the final details.\n\nWe had year had 4,370 participants on 3614 teams with over 39,403 submissions from 94 countries! For 948 users (including the 8th place finishers!, and 32 individuals in the Top 100), this was their first competition. We also had 87 new Masters or Experts at the conclusion of this 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\nAn extended congratulations to [Patrick0302](http://https://www.kaggle.com/patrick0302) who ended on top of the leaderboard on [the replica of the 1993 competition](https://www.kaggle.com/c/great-energy-predictor-shootout-i)! \n\nWe were excited to work with all the folks at ASHRAE, PSD Consulting, SinBerBEST, BUDS Lab, and Texas A&M, like Chris Balbach, Clayton Miller, Krishnan Kowri, and Jeff Haberl. We're glad they choose Kaggle to be a platform to bring these types of problems to the broader data science community. They've been a pleasure to work with, and we hope to work with them again in the future. Be sure to check out the work they put together at the ASHRAE [Winter](https://www.ashrae.org/conferences/2020-winter-conference-orlando) and [Annual meetings](https://www.ashrae.org/conferences/2020-annual-conference-austin-texas) this year.\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. Further, in this competition, many can use their machine learning skills to help a great cause like this one.\n\nWe've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, or believe you have evidence that suggests another team cheated, please contact [compliance](https://www.kaggle.com/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 host 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 have already seen your points and medals awarded, however it may take a few hours to propagate through if yours are still missing.\n\nIn the meantime, I've created this thread to be a curated list of your work. As you post your solutions, top kernels, and general discussion posts, I'll update this thread to keep track. If you write a paper, thesis, or present at a conference, and would like to share your work - please let us know so we can share with the Kaggle community! Additionally, if you performed any data manipulation, or maybe used a new technique in this competition that you'd like to share to further the industry, please let us know and we'll post it here! That way, should you be looking for takeaways in the future, or if you've just now stumbled across the competition, you have a place to see what surfaced from the work performed.\n\nHappy Modeling!\nKaggle Team\n\n###Top Solutions\n- [1st Place Solution](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/124709)\n- [2nd Place Solution pt 1](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/123481)\n- [2nd Place Solution pt 2](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/123528)\n- [3rd Place Solution](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/124984)\n- [4th Place Solution](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/124788)\n- [9th Place Solution](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/123525)\n- [13th Place Solution](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/123496)\n- [20th Place Solution](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/123654)\n- [46th Place Solution](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/123288)\n\n\n###Top Notebooks\n- [Comprehensive Data Exploration with Python ](https://www.kaggle.com/caesarlupum/ashrae-start-here-a-gentle-introduction)\n- [EDA for ASHRAE](https://www.kaggle.com/nroman/eda-for-ashrae)\n- [ASHRAE: Half and Half](https://www.kaggle.com/rohanrao/ashrae-half-and-half)\n- [Training LGBM by Meter Type](https://www.kaggle.com/corochann/ashrae-training-lgbm-by-meter-type)\n- [A Deep Dive EDA](https://www.kaggle.com/jaseziv83/a-deep-dive-eda-into-all-variables)\n- [KFold LightGBM](https://www.kaggle.com/aitude/ashrae-kfold-lightgbm-without-leak-1-08)\n- [Starter EDA and Feature Selection](https://www.kaggle.com/hmendonca/starter-eda-and-feature-selection-ashrae3)\n- [Simple Data Cleanup](https://www.kaggle.com/purist1024/ashrae-simple-data-cleanup-lb-1-08-no-leaks)\n- [AC/DC](https://www.kaggle.com/kailex/ac-dc)\n- [Simple LightGBM](https://www.kaggle.com/isaienkov/lightgbm-fe-1-19)\n- [Simple Exploration Notebook](https://www.kaggle.com/sudalairajkumar/simple-exploration-notebook-ashrae)\n- [What’s your CV method?](https://www.kaggle.com/kimtaegwan/what-s-your-cv-method)\n\n###Other Top Discussions\n- [Energy Prediction - Small Summary](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/112872)\n- [Findings from EDA](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/113678)\n- [Insights from Air Temperature Values](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/114483)\n- [Outlier Detection](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/122471)\n- [Site Specific Holidays](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/115256)\n- [Materials on Neural Network Forecasting - Focused on WaveNet](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/113007)\n- [Be careful of overfitting](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/113249)", "713465": "Congratulations for everyone!", "713488": "Thank you @sohier and @addisonhoward and the rest of the Kaggle team! And congratulations to the winning teams!\nIt was my first competition and I did learn a lot. I am preparing a repository with my solution and the code I developed to perform data cleaning, which I think might be helpful to others. I will share it here when it is ready.", "714776": "Can ASHRAE kindly publish the «solution» file and the uploaded solution files from say the three best algorithms from public and private LBs? This would be really very useful for research teams to continue and benchmark future algorithms.", "717347": "Congrats to everyone! We really appreciate everyone's participation in the competition. Thanks for everyone's patience despite the hiccups. We really believe that this competition succeeded in getting the building science and data science communities to understand each other better! I know I learned quite a bit.\n\n**We are in the process of curating a directory of Notebooks for building performance engineers and analysts from the competition that will serve as a recipe book for beginners as well as experts who are curious to learn about certain topics. We highly encourage you all to share your solutions as a notebook for this purpose. We will acknowledge the authors of all notebooks in this process, so please annotate your notebook or profile with how you would like to be acknowledged. It would also be helpful if you could indicate whether you are an ASHRAE member.**", "717348": "yes! We plan to organize and publish as many of the top solutions as possible, including the top 5", "717349": "yes! please share :)", "724386": "congratulation to all....appreciated for their hard work....", "725556": "Are you planning to release the test set with ground truth values?", "727285": "Is ASHRAE planning to release the complete test set with ground truth values?" }, "source": "meta" }