💳 Classifying credit applicants [Presentation][Report]
The goal of this study is to determine, in an automated manner, whether new applicants present good or bad credit risk. Several machine learning models are trained to classify applicants based on their credit rating. A random forest is found to be the best performing model, which ascertains the checking account status, credit duration, credit history, average balance in savings account, and credit amount, to be the most decisive information for classification.
Tested ML models:
- Logistic regression
- Neural networks
- Decision trees
- Random forest
- LDA
- KNN
- SVM
- Naive-Bayes
- Combination
