Estimating-Loan-Default-Probability

IBA ML2 Mid-project / Kaggle Competition

This porject is intented to build the most accurate model for predicting the porbability of loan default. We have two different datasets. 'Train.csv' consists of all features and target column, on which the model is built. 'Test.csv' consists of only feature columns except target column and the final submission in Kaggle is done with this dataset.

The EDA part of the project is preformed on a separate notebook in detail.

To get the highest accuracy possible, I tended to use Boosting Algorithms which preforms better than other traditional ML algorithms.