Optimized Ensemble Learning For Advanced Breast Cancer Detection Accuracy

: Early breast cancer detection is crucial for improving patient outcomes, yet remains a challenging task. This research enhances breast cancer classification by analyzing the Wisconsin Breast Cancer Dataset and combining four machine learning models: Logistic Regression, Support Vector Classifier, Random Forest, and XGBoost. Each model was fine-tuned using Bayesian optimization to maximize performance. To improve prediction accuracy and reliability, an ensemble system was created with a weighted voting classifier, assigning more weight to betterperforming models. The resulting model achieved 98.25% accuracy, demonstrating the power of ensemble learning and optimization techniques in developing efficient, and reliable tools for breast cancer diagnosis.