This is my resolution for a kaggle competition on life insurance assessment classification
In this dataset, you are provided over a hundred variables describing attributes of life insurance applicants. The task is to predict the "Response" variable for each Id in the test set. "Response" is an ordinal measure of risk that has 8 levels.
- Data Analysis
- Missing Data Imputation
- Imbalanced Data
- Pipeline
- Categorical Variable Encoding
- Hyperparameter Optimization