Healthcare Insurance Data Analysis

Overview

This project analyzes healthcare insurance data to identify factors driving medical costs and segment high-risk individuals.
The analysis focuses on age, BMI, smoking status, and region to provide actionable insights for insurers.

Objective:

Identify key drivers of medical insurance charges and recommend strategies for cost reduction and risk management.

---

Dataset

• Source: Kaggle - Medical Cost Personal Dataset
• Size: 1 CSV file, ~7,000 records
• Columns:

  Column	Description
  age	Age of the customer
  sex	Male / Female
  bmi	Body Mass Index
  children	Number of dependents
  smoker	Yes / No
  region	Customer region in the US
  charges	Medical insurance cost (target)

---

Tools & Libraries

• Python (Pandas, NumPy, Matplotlib, Seaborn)
• Google Colab
• Power BI for dashboard visualization

---

Steps

1. Data Cleaning

• Checked for missing values and duplicates
• Ensured correct data types
• Created derived columns:
  • Age Group: Young / Adult / Senior
  • BMI Category: Underweight / Normal / Overweight / Obese
  • Risk Level: Low / Medium / High based on age, BMI, and smoker status

2. Exploratory Data Analysis (EDA)

• Compared average charges by smoker status
• Analyzed charges vs age and charges vs BMI
• Checked regional cost differences
• Visualized risk-level cost patterns using boxplots

3. Segmentation

• High Risk: Smoker OR Obese OR Senior
• Medium Risk: Adult OR Overweight
• Low Risk: Young, Non-smoker, Normal BMI
• Calculated average charges per risk group

---

Key Insights

• Smoking is the biggest cost driver — smokers have 3–4x higher charges.
• Older age and higher BMI correlate strongly with higher costs.
• High-risk customers contribute disproportionately to total medical expenses.
• Regional differences are minor compared to smoking or BMI effects.

---

Recommendations

• Wellness Programs: Encourage high-risk customers to join preventive care programs.
• Premium Adjustments: Adjust insurance premiums based on risk level.
• Targeted Awareness: Educate high-risk segments about lifestyle impacts on costs.
• Preventive Interventions: Offer regular checkups or incentives for early detection.

---

Visualizations

• Scatter plots: Age vs Charges, BMI vs Charges
• Boxplots: Region vs Charges, Risk Level vs Charges
• Smoker vs Non-smoker average charges bar chart

---

• Performed data analysis on 7,000+ healthcare insurance records to identify cost drivers like smoking, age, and BMI.
• Segmented customers into Low, Medium, High Risk groups and calculated average medical charges.
• Delivered actionable insights for insurers, including wellness programs and premium recommendations.
• Visualized patterns using Matplotlib and Seaborn, highlighting age, BMI, region, and smoking impacts.