/Credit-Risk-Evaluaion

Build and evaluate several machine-learning models to predict credit risk using free data from LendingClub.

Primary LanguageJupyter Notebook

Credit Risk Evaluation

In this assignment, I was assigned to build and evaluate several machine-learning models to predict credit risk using free data from LendingClub. Credit risk is an inherently imbalanced classification problem (the number of good loans is much larger than the number of at-risk loans), so you will need to employ different techniques for training and evaluating models with imbalanced classes. You will use the imbalanced-learn and Scikit-learn libraries to build and evaluate models using Resampling and Ensembling technique:

Summary for Resampling Notebook

Which model had the best balanced accuracy score?

> SMOTEENN Model

Which model had the best recall score?

> SMOTEENN Model

Which model had the best geometric mean score?

> SMOTEENN Model

Summary for Ensembling Notebook

Which model had the best balanced accuracy score?

> Easy Ensemble Classsifier

Which model had the best recall score?

> Easy Ensemble Classsifier

Which model had the best geometric mean score?

> Easy Ensemble Classsifier

What are the top three features?

> Precision, Recall and F1