# First Silver Medal - Over The Moon!

I have no clever solutions to share, but I'm thrilled to score my first silver medal in a Kaggle competition, so I'll briefly share my approach, especially because it might be helpful for others who are relatively new to Kaggle (or non-playground competitions).  I couldn't devote much time to this competition - in the end, I only had 24 submissions, of which 5 threw errors during submission (mostly related to installation problems), so only 19 valid submissions. Whatever experiments I performed were only possible due to the generosity of fellow Kagglers who shared their solutions via public notebooks. I would like to thank them all, but especially
[@cdeotte](https://www.kaggle.com/cdeotte)
,
[@yekenot](https://www.kaggle.com/yekenot)
,
[@eikyou](https://www.kaggle.com/eikyou)
,
[@albansteff](https://www.kaggle.com/albansteff)
,
[@kendontcare11](https://www.kaggle.com/kendontcare11)
,
[@andreasbis](https://www.kaggle.com/andreasbis)
and
[@omidbaghchehsaraei](https://www.kaggle.com/omidbaghchehsaraei)
Since I had some experience with tabular competitions due to being a regular competitor in the Tabular Playground Series on Kaggle for a year, I knew that GBDTs and NNs were likely to combine well, and I focused on building such ensembles. About 2 months ago, I'd narrowly missed my first medal due to trusting the LB over my CV, so I focused on my CV, with a goal of CV >= 0.685 and LB >= 0.69. But until the last day, I couldn't cross CV = 0.683, even though some of the submissions were in the 0.689-0.691 range on the LB. Entering the final day, I was outside the Top 1000, & sorely tempted to submit the top scoring public notebook, which I'd been avoiding because of a large LB-CV gap. Finally, when I started to play around with weights, I managed to push the CV past 0.685 for the first time - with 2 hours to go, I finally re-entered the Top 1000 (at 787), and my final two submissions were ones that finished with less than half an hour to go (CV = 0.686, LB = 0.693; CV = 0.682, LB = 0.690). I deliberately didn't choose my second-highest scoring submission on the LB, because it was a variant of the top scoring one. I also didn't select the submission with the highest CV (CV = 0.687, LB = 0.687), because the LB, while equal to the CV, was too low compared to several other submissions. In the end, the gamble paid off, and I was on the right side of the shakeup, moving up (657 spots) to 130 and earning a silver, my first medal. I'm very aware of how big a role many others (named above) played in this, but I'm still happy with my experiments, and especially final selections.
I'd like to end by thanking everyone whose work I built on once again, and congratulating all the winners. Looking forward to more competition, learning and fun - Happy Kaggling, everyone!