Skip to content

creating a credit risk assessment algorithm to help classify the risky loan demands from the good ones.

Notifications You must be signed in to change notification settings

mlachha/Credit_Risk_Analysis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Credit_Risk_Analysis

Overview

The purpose of this analysis was to help create a credit risk assessment algorithm. Credit risk is an inherently unbalanced classification problem as good loans easily outnumber risky loans.

in order to accurately predict credit risk. we used :

  • Naive Random Oversampling
  • SMOTE Oversampling
  • Cluster Centroid Undersampling
  • SMOTEENN Sampling
  • Random Forest Classifying
  • Easy Ensemble adaBoost Classifier

Results

With each of these methods we split the data into training and testing datasets, applied the corresponding transformations, and then compiled accuracy scores, confusion matries, and classification reports to showcase the results, here are the results for the different models that have been attempted :

Naive Random Oversampling

picture

SMOTE Oversampling

picture

Cluster Centroid Undersampling

picture

SMOTEENN Sampling

picture

Random Forest Classifier

picture

AdaBoost

picture

Conclusion

after looking at the result of our models we realise that sampling didnt cause much improvement in the models results.

and with respect to the chosen model in this case we chose the Easy Ensemble Classifying model, with the Adaboost algorithm as it does a great job detecting the high risk and thats whats of the most importance to us in this case.

About

creating a credit risk assessment algorithm to help classify the risky loan demands from the good ones.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published