Destination Country Prediction of a New User's first booking, using Multinomial Classification Algorithms, combining data from 4 different CSV files, having user details, along with their demographics, signup properties, 10 lac rows of web session records for the users. Main dataset had 2.2 lac rows train, 62K test data. The dataset was provided by AirBnB. With this model, the company can decrease the average first booking time, and better forecast demand.
Metrics: Accuracy: 0.672