Medical-care-cost-analysis

This project utilize multiple regression to analyse driving factors for medical care cost. The data structure can be found in the relational schema. The code is written using R and contains four parts:

1. Data cleaning and reshaping, feature extraction.
2. Exploratory data analysis.
3. Divide train and test dataset. Multiple regression, multiple regression with transformation, AIC model selection using traning dataset.
4. Model prediction on test dataset.