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.
We 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. In this challenge, CAIS is asking you to build a predictive model that answers the following question:
“How many deaths, recoveries and cases occur per a given date and province?”
Though this competition is just for fun as winners are eligible to win prizes, building predictive models can have a real-world impact. Here’s a list of ways that predictive models for a global outbreak can make an impact.
- Predictive modelling aids in public health planning and response.
- A predictive model would help allocate medical resources and determine preventive measures more efficiently.
- A predictive model could also educate the public and policymakers at all levels on their decision-making process.
- A predictive model applied to different provinces could help to gain an understanding of the evolution since factors may vary from one province/territory to another.
Start Date: October 4th, 2020
Checkout the workshops we’re offering throughout the competition.
End Date (Final Submission Deadline): January 3, 2021, 11:59 pm EST
Top 10 Teams Announced: January 4, 2021, 9:00 pm
Top 10 Teams presentations: Sunday, January 17, 2020 ( Time TBA )
You may submit a maximum of 5 entries per day. You may select up to 2 final submissions for judging.
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.
Please 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.
The 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.
All teams, regardless of place, are also strongly encouraged and invited to publish a manuscript of their solution (and open source their code, if willing).
How to Enter
- Visit this URL kaggle.com/c/cais-x-t1-2021/overview
- Sign in or create a Kaggle account
- Click on the Rules tab and read the rules
- Click on the “Join Competition” button
- Start hacking away!
The 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:
The final score is the mean of the RMSLE over all columns.
For every date and province pair in the dataset, submission files should contain four columns: “ForcastId”, “# Deaths”,”# Confirmed_Cases”, and “# Recovered”.
The file should contain a header and have the following format:
ForcastId ,# Deaths,# Confirmed_Cases,# Recovered 1,1,7,7
Interested in learning more about the CAIS X? Need some help getting started? Click the images below to learn more about these workshops!
Past workshops have a youtube recording you can refer to at any time.
Interested in all of our workshops? Check out our website carletonai.com/events
The rules are posted here as a convenience, official rules are found on the official Kaggle competition rules page.
1. One account per participant
You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.
2. No private sharing outside teams
Privately 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.
3. Team Limits
The maximum team size is 2.
In 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.
5. External Data
You 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.
6.Use of Open Source.
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.
CAIS 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.
8. Rules change
CAIS 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.