# Lessons learned from a 95 position drop (Public 11th place)...

First of all, thanks to my teammates @applehph, @fergusoci, @m7catsue, and @mahluo for all of their hard work over the past month. We had high hopes finishing the competition in gold contention with our public LB position of 11th place, however it didn't work out that way in the end. We still ended it with a silver medal, so I'm still very proud of how our team performed!
Like all of these competitions, you come away with something new to remember and apply to future competitions. For our team, I feel there are two distinct lessons that we learned:
1) Never underestimate ensembling or stacking diverse models
Our final two submissions we chose were single LGB models. We made that decision mostly because we never saw good effects in our CV and LB when ensembling a variety of models (or even multiple different LGB models). However, the ensemble solutions we didn't pick actually turned out to perform best on the private dataset. This points to an important truth of simply relying on good practices. And ensembling is a good practice.
2) A correlated CV and LB is crucial before any more work should be done
That leads me to point number 2. It is very difficult to make good decisions on features and best model parameters if you don't have a correlated LB and CV. We were unable to make a good decision on ensembling because we had trouble in this area. We don't need them to be exactly mirror images of each other, but when CV goes up we should expect to see LB go up. And if they don't, then figure it out...or rely on CV!
Anyways, we learned a lot and I'm excited to bring this knowledge into the next competition. Thank you Kaggle, congrats to everyone, and job well done!