Sendy Logistics Challenge
$7,000 USD
Predict the estimated time of arrival (ETA) for motorbike deliveries in Nairobi
23 August–25 November 2019 23:59
1148 data scientists enrolled, 431 on the leaderboard
Outliers
published 11 Sep 2019, 11:27

Dataset has many outliers, but droping them disimprove result. Has anyone guess why?

Better way is to use Robust Algorithm to deal with outliers

what kind? like HuberRegressor? or more like winsorizing and more preprocessing on the data?