# Congratulation to everyone!!!

Hello all, congratulations to the winner, gold medalists,, and especially to those who survived the shake-up :)
I got busy with my work and had to stay away for 4 weeks without doing anything, now looking back that may have prevented me from overfitting my model further!
The shake-up seems to be quite strong, and I am not entirely sure what worked in my solution and what didn't.  I am pretty sure the following were helpful:
feature selection by the mean of feature permutation
a significant amount of pseudo labelling, even concatenating multiple copies of test data and predict label. one of my best single models was 3 x pseudo labels with public 3.668 private 3.600, but sadly I didn't select it
a little moderated post-processing for prediction with more than 0.50 probability seems to help - I used a formula of binary_probabilityX1.1XOUTLIER_VALUE, which helped to improve my best final submission
anyway, I have learnt a lot throughout this competition -- even though I didn't have much as fun as I would like to - competing by yourself is hard, turning down team-up invitation from friends is HARD, getting that solo gold is VERY HARD!
See you all around the LB!!!!