Breast cancer is one of the deadliest diseases impacting women worldwide, taking many lives. However, with early discovery and proper treatment, the odds of survival increase dramatically. The rise of machine learning (ML) has had a significant impact on healthcare, notably in terms of managing the increased incidence of breast cancer. While traditional approaches frequently struggle to analyze the massive volumes of data involved, machine learning techniques are becoming increasingly popular due to their ability to improve detection and diagnosis efficiency. Accurate predictions are critical for reducing unneeded treatments and lowering patient expenditures. To resolve the class imbalance between benign and malignant instances, the Synthetic Minority Oversampling Technique (SMOTE) is used. The model's performance is further refined using K-fold cross-validation (with k = 5) and hyperparameter tuning via GridSearchCV for various machine learning classifiers (MLCs), such as the K-nearest neighbors classifier (K-NNC), random forest classifier (RFC), support vector machine classifier (SVMC), and artificial neural network classifier (ANNC). Finally, the classifiers are evaluated based on accuracy, precision, recall, and specificity. Based on the experimental results, the K-NNC received the greatest overall score across all parameters, with accuracy around testing and an ACV of 98%. Furthermore, the overall average cross-validation score (ACV) improved for other models, despite significantly lower test results across all measures.