COVID-19 Risk Assessment & Projection Model

Personal Risk Assessment Web App. Testing Begins!

COVID-19 continues to affect countries around the world, and while the imminent approval of vaccines is much welcomed news, it will be many months before enough people are vaccinated to achieve herd immunity. In the meantime, we still need a data-driven, scientifically-sound way to quantify the risks of infection and reduce its spread.

This is why we are so excited to announce the launching of our Pandemonium personal risk assessment web app. for testing! The first phase of testing will be on a week-long rolling basis. We are starting off with a very limited feature set, which will be gradually expanded on a rolling basis. We hope to use the first phase testing to receive user feedback, resolve issues promptly and make improvements before we scale it up further.

Separately, we are raising funds in order to be able to take this further. We are targeting to raise $2,000 right away and hope to count on your generosity to help us scale up. We also need more volunteers with various skills, including non-technical, like legal, marketing, etc., as well as access to more data.

We welcome those interested to please help with our first phase testing to sign up at testing@pandemonium.dev. Those who wish to answer our call for donation can do so through our website at https://pandemonium.dev/.

This is a critical time in the pandemic and our risk assessment tool will complement the vaccines by assisting the public in mitigating their risks and making decisions congruent with those through better, more nuanced, quantitative understanding. Our app will be particularly useful not just in the next 2 months, but also as COVID-19 abates in 2021. It is not going to happen all at once, so it is not going to be easy for people to figure out on their own when it is safe enough to do certain things they may have held off doing.

While the app appears very simple to the user, it has a sophisticated Stochastic Heterogeneous Hybrid Spatially-Hierarchical/Dynamic and Demographically-structured Regional Susceptible-Exposed-Infectious-Recovered-Dead (SEIRD) Compartmental model built on the Pyro Probabilistic Programming Language (PPL), using Markov Chain Monte Carlo (MCMC) and other statistical inference techniques.

We sincerely hope that you can share your comments and suggestions with us.

This effort is being led by Quantum Risk Analytics, Inc., recently founded by MIT alumni, and has project member contributors from around the world.

Core team:

We are developing a free, powerful web tool that is highly informative and can be used by anyone.

Key differences from many other models:

 

More about this project can be found in this working draft proposal.

Check back soon.... This site will be updated further.

Help Wanted! If you can contribute to this project in any way, please contact us! This is an all-volunteer effort so far.

Questions? E-mail us.