Skip to content

Latest commit

 

History

History
2 lines (2 loc) · 430 Bytes

README.md

File metadata and controls

2 lines (2 loc) · 430 Bytes

Classification of Income Groups | Census-Income Database US

Used Different visualization techniques to formulate the hypothesis followed by data cleaning and preparation. Use of imbalanced data techniques such as Oversampling and Undersampling methods, and SMOTE were imployed. Finally Naive Bayes algorithm was used to classify the target variable into income groups and XgBoost was used to improve the accuracy of the model.