# Sharing Solution of Rank 23 (0.88625 on Private LB)

For whoever is interested, here's my complete solution:
[https://github.com/rohanrao91/Kaggle_AirBnB](https://github.com/rohanrao91/Kaggle_AirBnB)
Briefly:
Built Logistic Regression on one-hot encoded features from sessions data as binary classifier for NDF vs non-NDF.
Built XGBoost on raw features, one-hot encoded features from sessions data, the logistic regression predictions from (1), with some basic feature engineering, and combining of features.
Didn't do too much of ensembling/blending/stacking since my CV and LB were not perfectly correlating, and hence stuck with these two single models. Plus, didn't have too much time :-)
Takes about 20-25mins to run on my 4GB MacBook Air.
Thanks to Kaggle and AirBnB for this fun challenge.
Congratulations to the winners and special Thanks to everyone who share their ideas, models, scripts, codes and solutions in the spirit of learning and making the Kaggle forums extremely rich in knowledge.