This research focuses on predicting Wisconsin Breast Cancer Disease using machine learning algorithm, employs a dataset offered by UCI repository (WBCD) dataset. The under- gone substantial preparation, includes managing missing values, normalization, outlier elimination, increase data quality. The Synthetic Minority Oversampling Technique (SMOTE) is used to alleviate class imbalance and to enable strong model training. Machine learning models, include SVM, kNN, Neural Networks, and Naive Bayes, were built and verified using Key performance metrics and K-Fold cv. included as recall, accuracy, F1-score, precision and AUC- ROC were employed to analyze the models. Among these, the Neural Network model emerged the most effective, obtaining a prediction accuracy 98.13%, precision 98.21%, recall 98.00%, F1Score of 97.96%, AUC-ROC score 0.9992. Study underscores promise of ML boosting the diagnosis and treatment of WBCD illnesses, giving scalable and accurate ways for early detection and prevention.