# 76th place solution with Kernel

First of all, thanks to Kaggle, the host and everyone who has actively shared ideas and kernels throughout the competition. My teammate
[@negi009](https://www.kaggle.com/negi009)
and I are excited with the silver medal and the 3 dots that is going to appear under our profile pic (Kaggle expert :P)
Model 1:
I had 5 lgbm models with GroupKFold CV and validation was done using truncated samples. I have included features from event data of games such as:
false-steps-average-per-round
,
game-time-average-per-round
etc. for each game. These features were showing higher feature importances but minimal improvement on LB score.
CV: 0.555, public LB: 0.545, private LB: 0.538
Model 2:
[@negi009](https://www.kaggle.com/negi009)
had xgb models with 4 GroupKFold CV with validation on truncated samples. Prior assessments in test sets are also included in train data. Within each fold he had truncated samples with 2 different seeds. So he had a total of 8 xgb models.
CV: 0.561, public LB: 0.547, private LB: 0.539
Model 3:
5 fold lgbm model from
[https://www.kaggle.com/fatsaltyfish/convert-to-regression-feature-test](https://www.kaggle.com/fatsaltyfish/convert-to-regression-feature-test)
Ensemble:
Final prediction is done using a custom voting function between all the above models. Out of the 18 models if an accuracy group gets more than 12 votes, it is selected as the final prediction. In all other cases, average distance from boundaries of model's thresholds has been used to determine the final prediction. This voting mechanism was giving stable results in multiple submissions as well as in public and private leaderboard.
Public LB: 0.549, private LB: 0.549