1,338 individual medical insurance records across four geographic regions. The data tracks seven demographic and health features including age, body mass index, and smoking status alongside the resulting medical charges.
Use Cases
- Develop a regression model to predict the 'charges' variable based on 'bmi' and 'smoker' status
- Conduct a correlation analysis between 'age' and 'children' to identify trends in total medical costs
- Analyze the impact of the 'smoker' categorical variable on the distribution of 'charges' across different 'region' values
- Train a random forest regressor to rank the importance of 'bmi', 'age', and 'children' in predicting annual insurance premiums
Strengths
- Contains 1,338 rows of individual insurance beneficiary data
- Includes seven distinct features: age, sex, bmi, children, smoker, region, and charges
- Captures four geographic regions within the United States to analyze regional cost variations
- Includes a 'smoker' column with binary 'yes' or 'no' values to indicate tobacco use