moamsa / medical-cost-clustering

Clustering using Insurance Dataset (Medical Charges)

Health insurance which covers the whole or a part of the risk of a person incurring medical expenses, spreading the risk over a large number of persons. We will apply Exploratory Data Analysis to be familiarized with the data. Then, we will implement K-Means and Hierarchical algorithms to divide the data point to some group with similar properties. The Table of content is as follow:

• About the Insurance Dataset
• Methodology
• Exploratory Data Analysis
  • Distribution of BMI, age and, charges
  • Distribution of gender, smoking, no. of children and residential area
  • Distribution of age
  • Features relationship
  • Effects of BMI categories, age and, smoking on charges
  • Correlation for different BMI categories
  • Effect of gender on charges
  • Effect of Resident Area on charges
• Clustering Algorithms
  • K-Means method
    • K-Mean: Charges - Age
    • K-Mean: Charges - BMI
  • Hierarchical clustering (Agglomerative)
    • Hierarchical : Charges - BMI
  • Future Work (K-Mode algorithm)
  View Jupyter NoteBook