Predicting movie revenue with AdaBoost, XGBoost and LightGBM

Marvel's Avengers: Endgame recently dethroned Avatar as the highest grossing movie in history and while there was no doubt about this movie becoming very successful, I want to understand what makes any given movie a success. I am using data from The Movie Database provided through kaggle. The data set is split into a train and test set with the train set containing 3,000 movies and the test set comprising 4,398. There are 22 features in both the train and test set, including budget, genres, belongs_to_collection, runtime, keywords and more. The train data set also contains the target variable revenue.