This project focuses on building a machine learning model to analyze and classify health insurance data. The main objective was to handle the class imbalance problem and improve model performance using advanced preprocessing and model optimization techniques.
The workflow began with data exploration and preprocessing, including handling categorical variables using Label Encoding and scaling the numerical features using MinMaxScaler. After preparing the dataset, the data was split into training and testing sets to build reliable machine learning models.
Since the dataset was imbalanced, the SMOTE (Synthetic Minority Oversampling Technique) method was applied to balance the classes by generating synthetic samples for the minority class. This helped improve the model’s ability to correctly detect minority cases and avoid bias toward the majority class. Handling imbalanced datasets is important because traditional machine learning models tend to favor the dominant class, leading to poor detection of minority outcomes.
After balancing the data, multiple machine learning algorithms were trained and evaluated. Hyperparameter tuning was performed using GridSearchCV combined with cross-validation to find the optimal parameters for each model and improve prediction performance.
The models were evaluated using performance metrics such as Accuracy, Precision, Recall, and F1-score to measure their effectiveness and ensure the model generalizes well to unseen data.
Overall, the project demonstrates a complete machine learning pipeline including data preprocessing, handling imbalanced data with SMOTE, model training, hyperparameter tuning, and performance evaluation, providing insights into how machine learning can be applied to healthcare insurance data analysis.
