Bankruptcy-Prediction-using-Machine-Learning

• Using various machine learning models (Gaussian Naïve Bayes, Logistic Regression, Support Vector Machine, Gradient Boosting Trees, Neural Networks) to predict whether a company will go bankrupt in the following years, based on 64 financial attributes of the company;
• Addressed the issue of imbalanced classes, different importance of each type of misclassification;
• Tune Parameters using Grid Search Cross Validation of best model GBM to achieve 0.96 accuracy, 0.62 recall and 0.77 f1 score;