Uber Nairobi Ambulance Perambulation Challenge
$6,000 USD
Can you use ML to create an optimised ambulance deployment strategy in Nairobi?
979 data scientists enrolled, 330 on the leaderboard
ConstructionTransportationHealthPredictionStructuredLocation
Kenya
17 September 2020—24 January 2021
Ends in 7 days
Is there a bug in the scoring of the submission file?
published 28 Dec 2020, 18:24

My assumption is that the order of the rows don't matter. However, I noticed that I get 2 completely differnet scores when the rows are sorted differently with the same generated submission file .

Anyone experiencing same or can @Zindi clarify if row arrangement matters by checking the arrangement in the scoring file. Happy to get your feedback.

perhaps the date is not checked?

Maybe. I guess Zindi needs to review and revert

Hello @Zindi.... Still expecting a response

This competition uses an external metric we set up outside the normal Zindi metric system, and it looks like the scoring function assumes the dataframe is ordered by date as in the submission file. Normally we can ignore row order because we're matching rows on an ID, here the idea is to look for the last specified location before a crash happens. I'll double-check and then get the team to put out a notice. My suggestion for now is to follow the ordering from the sample submission.

Thanks for the response. This will help me make progress with the development.