Welcome to the first-ever Carleton Artificial intelligence society Kaggle competition. This is a competition for Carleton University students to get experience in data science, machine learning and Kaggle competitions. We hope that you folks learn something out of this competition whether that be from our workshops or self-directed research that you've stumbled upon.
\n\nWe are currently living in a historical moment in human history. COVID-19 has affected everyone in the world in a major way. Universities and workplaces have been forced to remote work. You can't go anywhere in public without a mask and are greeted with hand sanitizer when you enter an establishment. Most importantly, the health crisis has had around 29 million cases and 920,000 deaths. \n\nIn this challenge, CAIS is asking you to build a predictive model that answers the following question:\n
\n
\n \"How many deaths ,recoveries and cases occur per a given date and province ?\" \n
\n
\n\n
Teams with the top 10 scores on the private leaderboard rank will move on to the next phase of the competition. The next phase of the competition will consist of teams presenting their winning solution to our panel. Our panel will be comprised of our sponsors and a few of our CAIS executives. After each presentation, the panel will give each team an individual score based on predefined criteria. When this phase of the competition is over, our panel will announce the top 3 teams based on their scoring. \n
\n
\n
\n\n\nPlease note that the panel will determine the winners of the prize money. Thus those who may have the best scores do not necessarily mean that they automatically win the competition. Teams who ultimately impress the panel with their solution and their presentation win the competition.\n\n
\n
\n
\n\nThe top 10 teams will be asked to publish a link to their open-sourced code on the competition forum. Also, teams are welcome to create a publicly available demo version of the model for more hands-on testing purposes. \n
\nAll teams, regardless of place, are also strongly encouraged and invited to publish a manuscript of their solution (and open source their code, if willing). \n\n
\nStart Date: October 4th, 2020\n
\nCheckout the workshops we're offering throughout the competition. \n
\nEnd Date (Final Submission Deadline): January 3, 2021, 11:59 pm EST\n
\n
Top 10 Teams Announced: January 4, 2021, 8:00 am EST\n
\nTop 10 Teams presentations: Sunday, January 17, 2020 ( Time TBA ) EST\n\n
\nYou may submit a maximum of 5 entries per day.\nYou may select up to 2 final submissions for judging.\n
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "# Evaluation\n\nThe evaluation metric for this competition is Root Mean Squared Logarithmic Error. RMLSE penalizes the underestimation of the actual value more severely than it does for the Overestimation. The RMSE is given by:\n\\[ \\epsilon = \\sqrt{\\frac{1}{n} \\sum_{i=1}^n (\\log(p_i+ 1) - \\log(a_i+1))^2 } \\]
\n\n\nThe final score is the mean of the RMSLE over all columns.\n
\n\nFor every date and province pair in the dataset, submission files should contain four columns: ForcastId ,\"# Deaths\",\"# Confirmed_Cases\", and \"# Recovered\". \n
The file should contain a header and have the following format:
\nForcastId ,# Deaths,# Confirmed_Cases,# Recovered", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "# Rules \n\n## 1. One account per participant\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n## 2. No private sharing outside teams\nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.\n\n## 3.Team Limits\nThe maximum team size is 2.\n\n# 4. Eligibility \nIn order to be eligible to participate in this competition, **you must be currently a Carleton University Student in the 2020 fall semester (September -December)**. In order to be eligible to win a prize, you may be asked to reproduce your scores with your models. So it may be in your best interest to save your models persistently.\n\n\n## 5. External Data\nYou may use data other than the Competition Data to develop and test your models and Submissions. In addition, you are not permitted to use data that contains information pertaining to the number of cases, deaths and recoveries on a provincial and national scale.\n\n\n## 6.Use of Open Source\n Unless otherwise stated in the Specific Competition Rules above, if open-source code is used in the model to generate the Submission, then you must only use open source code licensed under an Open Source Initiative-approved license (see www.opensource.org) that in no event limits commercial use of such code or model containing or depending on such code.\n\n\n## 7. Disqualification\nCAIS executives reserve the right to disqualify any participant from the Competition if any CAIS executive reasonably believes that the participant has attempted to undermine the legitimate operation of the Competition by cheating, deception, or other unfair playing practices or abuses, threatens or harasses any other participants.\n\n\n## 8. Rules change\nCAIS executives reserve the right to add or modify any rules listed above. Participants will be notified when any addition or modification has been made to the competition. ", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "FAQ", "content": "# What’s the difference between a private and public leaderboard?\nThe Kaggle leaderboard has a public and private component to prevent participants from “overfitting” to the leaderboard. If your model is “overfit” to a dataset then it is not generalizable outside of the dataset you trained it on. This means that your model would have low accuracy on another sample of data taken from a similar dataset.\n\n## Public Leaderboard\n\nFor all participants, the same t0% of predictions from the test set are assigned to the public leaderboard. The score you see on the public leaderboard reflects your model’s accuracy on this portion of the test set.\n\n## Private Leaderboard\n\nThe other 50% of predictions from the test set are assigned to the private leaderboard. The private leaderboard is not visible to participants until the competition has concluded. At the end of a competition, we will reveal the private leaderboard so you can see your score on the other 50% of the test data. The scores on the private leaderboard are used to determine the competition winners. Getting Started competitions are run on a rolling timeline so the private leaderboard is never revealed.\n\n# How do I create and manage a team?\nWhen you accept the competition rules, a team will be created for you. You can invite others to your team, accept a merger with another team, and update basic information like team name by going to the More < Team page.\n\nWe've heard from many Kagglers that teaming up is the best way to learn new skills AND have fun. If you don't have a teammate already, consider asking if anyone wants to team up in the discussion forum.\n\n# What are kernels?\nKaggle Kernels is a cloud computational environment that enables reproducible and collaborative analysis. Kernels supports scripts in R and Python, Jupyter Notebooks, and RMarkdown reports. Go to the Kernels tab to view all of the publicly shared code on this competition. For more on how to use Kernels to learn data science, visit the Read more about our decision to implement a rolling leaderboard on getting started competitions here.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "CAIS Workshops", "content": "Interested in learning more about the CAIS X? Need some help getting started? Click the images below to learn more about these workshops! \n\nPast workshops have a youtube recording you can refer to at any time. \n\n\n[](https://carletonai.com/event/first-kaggle-competition-submission/)\n\n\n\n[](https://carletonai.com/event/feature-engineering-techniques/)\n\n\n\n[](https://carletonai.com/event/introduction-to-scientific-python/)\n\n\nInterested in all of our workshops? Check out our website [carletonai.com/events](https://carletonai.com/events)\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }
1,1,7,7