Customer Churn Prediction Model with 96% Accuracy Using Random Forest

Developed a high-accuracy customer churn prediction model using Random Forest, achieving a 96% accuracy rate. The project involved extensive data preprocessing, feature engineering, and hyperparameter tuning to optimize model performance. Key features like transaction amount, revolving balance, utilization ratio, transaction count, and total CT change (Q4-Q1) were used to predict customer attrition effectively. The model provides actionable insights for identifying at-risk customers and designing targeted retention strategies, demonstrating strong analytical and problem-solving skills in predictive modeling.