AirQo Ugandan Air Quality Forecast Challenge
$5,000 USD
Predict future air quality levels and empower communities plan and protect their health
261 data scientists enrolled, 87 on the leaderboard
14 March—31 May
Ends in 2 months
data from airqo meta data
published 23 Mar 2020, 16:46

The data from Airqo has only 5 rows, hope it's will not cause many missing value when merging.

You have to perform a left join with the original dataframe by using location as the key. Obviously the NaN values will be replicated after joining.

thanks so much, you are showing the Leadership in community engagement.

Hello, I was hoping there was a place I could privately message you. It is regarding the Insurance prediction knowledge competition. https://zindi.africa/competitions/data-science-nigeria-2019-challenge-1-insurance-prediction. I have been using Catboost for the competition and I can't get past a 50%. You were the 2nd highest and I was wondering if you could share some tips with me. What model did you use, decision trees, KNN, XGboost etc., how did you engineer the features and any other things. My apologies for using another competiton as a discussion for this

This is for overfitting_PLB

Hello, I was hoping there was a place I could privately message you. It is regarding the Insurance prediction knowledge competition. https://zindi.africa/competitions/data-science-nigeria-2019-challenge-1-insurance-prediction. I have been using Catboost for the competition and I can't get past a 50%. You were the 2nd highest and I was wondering if you could share some tips with me. What model did you use, decision trees, KNN, XGboost etc., how did you engineer the features and any other things. My apologies for using another competiton as a discussion for this