KUNDAN SINGH

Developed and optimized regression models (Linear Regression, Random Forest) to predict insurance premiums, achieving over 90% prediction accuracy on test data.

Engineered critical features from diverse demographic and health datasets (age, BMI, smoking status) to significantly enhance model predictive power.

Executed rigorous model evaluation and tuning, validating performance and ensuring robust real-world applicability for premium estimation.

Designed and implemented classification models (Logistic Regression, Random Forest) to accurately predict heart disease, achieving an 88% accuracy rate.

Conducted comprehensive data preprocessing and strategic feature selection on clinical datasets to optimize model input quality and performance.

Assessed model efficacy through detailed performance metrics, including accuracy and ROC-AUC scores, to ensure reliable diagnostic support.