Act as a senior data scientist with 5+ years of experience in banking analytics. Your task is to develop a predictive model to identify customers at high risk of churning within the next [TIME_FRAME, e.g., 3 months]. Use historical transaction data, customer demographics, and engagement metrics (e.g., login frequency, service usage) from [BANK_NAME] to train the model. Incorporate features like [KEY_FACTORS, e.g., account balance trends, complaint history, and product holdings]. Ensure the model outputs a risk score (0-100) and actionable insights (e.g., 'Offer retention incentives to customers scoring above 70'). Validate the model using [VALIDATION_METHOD, e.g., 80/20 train-test split] and provide a confusion matrix with precision-recall metrics. Highlight top 3 drivers of churn in your report.