October 2024

In this project, I leveraged Python and advanced machine learning techniques to classify health insurance plans based on multi-year issuer data. The process commenced with comprehensive Exploratory Data Analysis (EDA) using Pandas, where I identified critical patterns and trends within the Health Insurance dataset, forming the basis for model development.

​

Following EDA, I executed thorough data preprocessing, which involved handling missing values, normalizing features, and encoding categorical variables to prepare the dataset for analysis. Using NumPy to derive meaningful insights that guided feature selection and engineering, I applied statistical methods, such as Standard Deviation, Mean, Mode, and Median.

​

The machine learning process included splitting the dataset into training and testing sets to evaluate model performance effectively. I developed four powerful Classification Machine Learning Models: K-Nearest Neighbors (KNN), Decision Tree, Logistic Regression, and Perceptron, which achieved an impressive accuracy of 97%. Hyperparameter tuning was conducted to optimize model parameters, ensuring robustness and accuracy.

​

To communicate my findings effectively, I utilized Matplotlib and Seaborn to create impactful visualizations highlighting key trends and model performance metrics.

​

This project showcased my proficiency in machine learning analytics and my ability to transform complex data into actionable insights, facilitating informed decision-making in health insurance offerings.

​

Business Opportunities:

​

• Personalized Health Insurance Plans: Utilizing the insights gained from the classification model, companies can develop tailored health insurance plans that meet the specific needs of different demographics, enhancing customer satisfaction and retention.

​

• Risk Assessment Tools: By accurately classifying health insurance plans, advanced risk assessment tools can be created, which would allow insurers to better predict claim costs and manage their portfolios, ultimately leading to more competitive pricing strategies.

​

• Targeted Marketing Campaigns: The data-driven insights can be leveraged to design targeted marketing campaigns aimed at specific populations, increasing the effectiveness of outreach efforts and driving enrollment rates.

 

Key Skills:

 

1. ​Exploratory Data Analysis (EDA)

2. Data Preprocessing with Pandas

3. Feature Engineering and Selection

4. Statistical Methods (Standard Deviation, Mean, Mode, Median) using NumPy

5. Supervised Machine Learning

6. Data Visualization with Matplotlib and Seaborn

7. Python Programming - Scikit-learn

​

​

** Click on the links below to see projects **