Disease forecasting project ideas
Help forecasters do better: document past model failures, port useful tools, teach the maths, or build early-warning datasets.
Researchers keep re-collecting the same numbers. Turn one of them into a clean, open dataset or API.
Shared data infrastructure speeds up every project that depends on it.
Output: A documented dataset or API.
Read the README and contributing guide, and get the project running locally.
Pick one small, well-defined piece of work (look for “good first issue”).
Say on the issue that you are working on it, then open a draft pull request early.
Ask for feedback while it is still small; respond to review quickly.
Write a short post about what you built and learned.
All steps done
Share what you made, then try another project. The PDF version has room for notes.
Help forecasters do better: document past model failures, port useful tools, teach the maths, or build early-warning datasets.
The source author’s top priority. Ideas range from DIY measurement to retrofit kits and modelling tools, and most need no lab.
Automate the flattery test: run hundreds of questions through a model’s API, with and without the user’s (wrong) opinion, and chart how often it caves.