Data Sprint 24 Tinder Millenial Match

In this notebook ,a Random Forest Classifier is used .A Baseline model is trained and scored using the validation data and then hyper parameter tuning is carried out using RandomizedSearchCV to find the optimal parameters and then feature selection with the aid of Boruta .Data preprocessing is carried out on both train and test data .These steps are shown in the notebook

2/16/2021
183 views