Boosting Techniques in Python: Predicting Hotel Cancellations

For this reason, boosting is referred to as an ensemble method. In this example, boosting techniques are used to determine whether a customer will cancel their hotel booking or not. Hotel cancellations represent the response (or dependent) variable, where 1 cancel, 0 follow through with booking. The relevant features to be included as the x variable in the boosting models are identified by the ExtraTreesClassifier. The three features identified by the ExtraTreesClassifier (excluding variables deemed to be theoretically irrelevant) are lead time, country and deposit type. The following boosting techniques are used in predicting hotel cancellations.