# chimps solution (#37)

Hi,
37ish is not too glamoourous but we worked very hard and I wanted to share our aproach :)
Our solution was based mainly in GNN which scored -2.317 provided by our team mate
[https://www.kaggle.com/jessky](https://www.kaggle.com/jessky)
and some lgb ensemble that scores a bit less than -2.1. Then our best nnet (bagged) scores almost -1.9. For lgb and nnet models we benefit a lot from oof predictions of FC. We kept adding different prediction and the score improved by ~ -0.4 just adding those. Besides some ad-hoc FE, we obviously made use of all the amazing distances and amazing calculations available in kernels. Mainly: acsf descriptors and the sergii distances (
[https://www.kaggle.com/criskiev/distance-is-all-you-need-lb-1-481](https://www.kaggle.com/criskiev/distance-is-all-you-need-lb-1-481)
)
Our final ensemble can be seen in here:
[https://www.kaggle.com/chechir/champs-ensemble](https://www.kaggle.com/chechir/champs-ensemble)
Thanks to the organisers,  and all the awesome kernel authors in this competition !