/Handling-Imbalance-data

This repository will compare the performance of different classification algorithms on various imbalanced datasets using multiple balancing techniques.

Primary LanguageJupyter Notebook

Handling-Imbalance-data

This repository will compare the performance of different classification algorithms on various imbalanced datasets using multiple balancing techniques.

Classification Algorithms:

  • Logistic Rgression
  • Support Vector Machines
  • Decision Trees
  • Random Forest
  • Naive Bayes

Balancing Techniques

  • SMOTE: We balanced the data in two ways a) Whole data b) Train data only
  • ADASYN same as in SMOTE
  • UNDER SAMPLING same as in SMOTE
  • ALGORITHMIC WEIGHTAGE
  • GAN same as in SMOTE

Datasets

  • Fraud
  • Churn
  • BankMarketing