Data exploration and visualization.
Preprocessing the train data: feature engineering, outliers removal, handling missing values and categorical features, data scaling and dimensionality reduction.
Performing 4 machine learning algorithms on the train data, using the validation set to choose the best hyper-parameters that will prevent overfitting and evaluation of the models using K-fold cross validations and ROC curves.
Using the model with the best results to prefict the test data.
Project done with Python on Jupyter notebook with Scikit-Learn.