# Feature Engineering and Ensemble Architecture (7th place)

Congratulations again to all the Winners!! I believe that top winners will give many valuable insights soon. :)
In this post I would like to share some of our findings and experience in NLP, feature extraction and feature selection tasks, and also my ensemble architecture. Feature engineering helped us a lot in improving the performance of our different models.
Here I write only about my own parts and I think @Darragh (Pearson correlation analysis to submissions) and @CodingNeo would share their amazing parts later.
Due to the limitation of Web editor, I cannot show my post in well format here. So please check the following link to download and see full post:
[https://drive.google.com/file/d/0B-20iuF5gIcyQWtpOVlnTTREX3M/view?usp=sharing](https://drive.google.com/file/d/0B-20iuF5gIcyQWtpOVlnTTREX3M/view?usp=sharing)
R example code for RFE and Boruta feature selection can be downloaded from the attachment.
This is my first time to share the details of my feature engineering and ensemble architecture in Kaggle. Please feel free to give any comments.
Hope it can help other kagglers to some extent. :)
Best regards,
Mark Peng