Submissions will be evaluated using range normalized mean absolute error (MAE) to quantify the difference between the predicted values and the observed values. For the purposes of scoring, all variables will be treated as continuous variables and each missing instance will be given equal weight. 

The final ranking will be determined by performance on the held out test sets only (private leaderboard). The private leaderboard will be revealed 7 days after submissions close and winners will be announced at the [UCSF Digital Health Hub Awards 2022](https://www.ucsfhealthhub.com/awards/2022/home) on November 14th. Participants are not required to attend the UCSF Digital Health Hub Awards.

First place: $10,000 USD
Second place: $5,000 USD
Third place: $2,500 USD

• Final submissions must include a method description of at least 400 words and not more than 1,000 words (excluding references)
• The Competition Sponsor requires the code for final Submissions to be released under an Open Source License