Welcome challengers! The COVID Computational Challenge seeks to create an innovative solution to determine the risk of exposure to COVID-19 in locations in and around the City of Los Angeles. This two-week challenge will provide ideas and concepts to help deepen our understanding of the issues that may increase or decrease COVID-19 exposure risks, how to calculate these risks, while being respectful of data privacy. Projects will be reviewed by a panel of judges from the City of LA, LA County Department of Public Health, Chamber of Commerce, and academia.
*You must be signed in first to access
Welcome challengers! The COVID Computational Challenge seeks to create an innovative solution to determine the risk of exposure to COVID-19 in locations in and around the City of Los Angeles. This COVID-19 risk scoring is for various locations like shopping malls, meeting spots, office centers, restaurants to provide guidance for risk mitigation to serve our LA communities. The solution must also incorporate the ethical protection of individual data and respect data privacy norms. Projects will be reviewed by a panel of judges from the City of LA, LA County Department of Public Health, Chamber of Commerce, and academia.
Winning Solutions See Award Ceremony
Team Contemporary Li Shi Jen (当代李时珍) with members Wanying (Joy) Qian and Jessie (Ge) Qu from University of Michigan and Pengyue Jia and Yi'an Wang from Zhejiang University. Their mentor is Professor Feng Zhang from Zhejiang University.
Rising Star in Data Science
Team HDMA with Daniel Kao with mentor Professor Ming-Hsiang Tsou from The Center for Human Dynamics in the Mobile Age.
June 2 at 11 AM PST
Risk Scoring Solutions Discussions led by RMDS
June 3 at 3:00 PM PST
Public health perspective on COVID-19 data issues
June 1 at 2 PM PST
Training by SafeGraph on Social Distancing and Mobility Data
May 27 at 10 AM PST
Training by SafeGraph on Social Distancing and Mobility Data
May 27 at 2 PM PST
Training by the City of LA and RMDS on the problem statement, data, evaluation, and resources
May 28 at 3:30 PM PST
Training by UCLA Computational Medicine on analyzing the trajectory of COVID
May 29 at 10 AM PST
Training by ESRI
May 29 at 2:00 PM PST
Training by Gartner on Data Bias and Ethics
In the next two weeks, you will determine the risk of exposure to COVID-19 in locations in and around the City of Los Angeles.
Features that may increase or decrease COVID-19 exposure risks
Assist with the transition to re-open by predicting location-based risk scores
Proposed methodology to implement risk score assessment
Actionable steps for risk mitigation and to improve risk score
Participants are highly encouraged to use the open data resources highlighted below. If proprietary data is used, it must be documented for our judges to understand and reproduce your work. The datasets below contain both static and time varying spatial-temporal features related to COVID-19. Documentation included on site.
Open Data Portals:
To get started, you can begin with these datasets. View Dataset
Free training on epidemiology, spatial analytics, data science, and more:
- Analytical Workflow Guidebook
- Intro to epidemiology
- Data Science Fundamentals
- Ethics and Bias in AI Systems
- Big Data Applications in COVID-19
- Intro to Mobility Data in COVID-19
- Webinar Series Data Science and COVID-19
- Risk forecasting for UK
- Detecting Suspected Epidemic Cases Using Trajectory Big Data
- Source code required
- README file explaining how to run your codes. If you use Java or C++, please also include the commands you use to compile your code (we should be able to compile, and if necessary, run your code and see the output files generated).
- Technical Report in PDF with names of all team members and team name required
- Your report should include the following sections: Introduction, Data, Methodology, Result, Implementation Proposal, Risk Mitigation Recommendations, Acknowledgement, and Reference. Please refer to the Problem Statement to check that your solution answers the prompt.
- CSV of your results with the location and location-base risk score
- Optional is presentation and demo recording
Impact: what useful business insights are acquired from the proposal? Does the score and implementation proposal have a meaningful impact on businesses and the LA community? What are actionable steps recommended to improve their score?
Methodology Validity: are the methodology, mathematics, and epidemiology principles behind the proposal reasonable and documented? How is the risk score and thresholds defined and are the ways that risk is quantified and factors are weighted sensible? Are the assumptions and limitations of the methodology clearly outlined with suggestions to improve the proposal? Are the quantitative steps of data ingestion, feature engineering, model architecture and performance optimization valid? How robust is the model?
Reproducibility: do the solution and script use best practices with workflows and documentation to reproduce their work? For example, are the data ingress and egress pipelines reproducible? Is there a clear presentation of data science work in the documentation?
Usability: is the information presented in a way that is actionable? Would a member of the general public understand the score, what it means and what actions to take?
Ability to Deploy: is getting access to the data realistic with reasonable computation time? Is the proposal a good fit within the existing system? Is the system scalable and robust to take into account new data sources, maintenance and perhaps even applications to other cities?
Fair and Ethical Use of Data: does the solution take into account biases in data related to underserved communities? Is the data from open and trusted sources?
Innovation: will the idea have a big impact? How innovative is the approach, selection and weighting of risk factors, or how information is displayed and communicated?
Inclusiveness/Diversity: the team working on this should represent diverse views across gender, ethnicity, and age. Does the solution provide insights that factor demographic variables and its relationship to risk? Does the solution provide context, specifically focused on intended outcomes towards equitably assessing locations (e.g. inclusiveness/diversity methodology section in report)?
Stage 1: Registration
Each team member will register on GRMDS. Be sure to check the box stating your intent to register for the data science competition. We will send out a confirmation email to all candidates upon successful registration. Add info about your team in the Team Registration Form. For any questions, please email: firstname.lastname@example.org.
Stage 2: Team work and submission
Submissions must include all the coding, CSV file of your risk score predictions, and technical report and are due Monday June 8 at 11:59 PDT. Please upload all deliverables to the GRMDS. Place the names of all team members and team name on the technical report. Submission by any individual group member will represent the whole team.
Stage 3: Evaluation and Final Presentation
Our expert committee from Chamber of Commerce, City and County of LA, RMDS, and academia will evaluate all project deliverables and select the finalist teams. The evaluation criteria will be disclosed in the future announcement. The city of LA may work with partners to deploy and use the winning models to score risks to guide our communities in the form of alerts accessed via map, website, or app
Cash prizes, internship opportunities, and certificates of participation will be awarded for first and second place. Teams will also be awarded for most ethical consideration and most reusable code or algorithm.
Cash prizes of over $3K
Considerations for internship positions at the City of Los Angeles, UCLA Computational Medicine, and other partner organizations
1on1 mentorship with data executives
Recommendation of winners’ technical report for publishing at Harvard Data Science Review magazine
Certificates for winners and contestants who make a complete submission
Invitation to present at IM Data 2020
Code of Conduct
The use of data will adhere to ethical use and protection of individual data privacy. Find the Code of Conduct here
Frequently Asked Questions
The registration form can be found here. (You must be signed in to view the form.)
Participants are welcomed either as individuals or as teams. In the case of teams, one person must be designated as the team leader and will be solely responsible for communications with the organizers.
For Mentors, we’re seeking members of the business, academic, and research community. We ask our Mentors to hold office hours for 2 hours per week for the two-week duration. To register as a Mentor for the competition, please go to the link here.
Submissions can be made here. See above section “Submission Deliverables” to see what must be included in your submission.
There is no deadline for our registration. But we strongly recommend that your registration is no later than 05/29 since you need time to prepare your work.
No minimum or maximum number.
The number of team members will not impact potential prize offerings. The prize offerings will remain the same.
Yes. We welcome people from different cities or countries to join our competition. This competition is open to the global community.
If you have any questions, please email: email@example.com. We’ll get back to you as soon as we can.
If you need to update your team roster, fill out the form here
Please see resources listed on this page, including recordings of competition training sessions. There is also a dataset starter list and further reading material here.
You may find mentors and email them here with any questions or requesting feedback on your work.
Please fill out the form here. If any further questions you could email us at firstname.lastname@example.org with any questions or requesting feedback on your work.