[Kaggle - Where will a new guest book their first travel experience?] (https://www.kaggle.com/c/airbnb-recruiting-new-user-bookings)
The goal of this competition was to predict where a new Airbnb user will make their first booking, using demographic data, web session records and some further summary statistics.
There were 12 possible destinations and the evaluation metric for the competition was Normalised Discounted Cumulative Gain @ 5.
The solution obtained a rank of [31st out of 1462 competitors] (https://www.kaggle.com/c/airbnb-recruiting-new-user-bookings/leaderboard/private).
- Create a working directory for the project
- [Download the data from Kaggle] (https://www.kaggle.com/c/airbnb-recruiting-new-user-bookings/data) and place in the working directory.
The files required are:train_users_2.csv
,test_users.csv
andsessions.csv
. - Run
users_sessions.py
- Run
xgb_bag.R
- MySQL
- Python 3+
- R 3+