Data ethics
Use publicly available or fully de-identified datasets only — no identifiable patient data, personal health records, or data you don’t have the right to use. Cite every dataset’s source and licence in your README.
Build a data-driven system on real, empirical datasets that solves a problem in healthcare or finance — backed by data engineering that turns raw input into something a person could act on.
Build a data-driven system on real, empirical datasets that solves a problem in healthcare or finance. That means predictive models, diagnostic pipelines or automated financial systems, backed by data engineering that turns raw input into something a person could actually act on.
Example directionsUse publicly available or fully de-identified datasets only — no identifiable patient data, personal health records, or data you don’t have the right to use. Cite every dataset’s source and licence in your README.
Never operated on real patients, real clinical decisions or real money. Trading systems run in simulation or on historical data only.
Every submission is a research prototype — not a medical device, not a diagnostic tool, not financial advice. Your README must say so.
Your project must be built on empirical, real-world data and implement predictive machine learning, a diagnostic pipeline or an automated financial system.
Judges score each project only against its own track’s criteria. Ties are broken by the first criterion listed.
How novel is the invention? Does it address a genuine medical, scientific or financial need with measurable impact?
Does the prototype actually work? Quality of design, code and engineering methodology.
Quality of research, experimental design, data collection and validation of the approach.
Clarity of the demo, explanation of the invention and the ability to communicate its value to judges.