This repository has been archived by the owner on Jun 22, 2022. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 170
Competition summary
Miłosz Michta edited this page Sep 3, 2018
·
1 revision
- Interest rate feature * *
- Adding PCA, T-SNE, Denoising autoencoders * for feature extraction *
- Build model to fill NaN's
- Dedicate more time for neural networks like RNN, 1-D Convolution for time series *
- Using oof prediction from experiments evaluated by grid/random/bayesian search *
- Trust your CV!
check our GitHub organization https://github.com/neptune-ml for more cool stuff 😃
Kamil & Kuba, core contributors
- chestnut 🌰: LightGBM and basic features
- seedling 🌱: Sklearn and XGBoost algorithms and groupby features
- blossom 🌼: LightGBM on selected features
- tulip 🌷: LightGBM with smarter features
- sunflower 🌻: LightGBM clean dynamic features
- four leaf clover 🍀: Stacking by feature diversity and model diversity