Hello everyone👋 and Congrats to the winners.
Here is my solution link. It is an ensemble of XGB and LightGBM trained on 10 stratified folds with oversampling method for the data imbalance problem and some threshold variations. It has a score of 0.761 on the private LB but was not one of my 2 best public LB scores.
please don't forget to upvote if you find it useful🙏
Enjoy!
Nice work @Ska3rfon, I and my team mate also made use of such approach we got 0.7631224764468371 on the private leaderboard but we didn't select it as our best submission 😔
Thanks!