Breast cancer is one of the most common invasive diseases affecting women globally, representing a significant public health concern. It develops from aberrant cell proliferation in breast tissue and, if untreated, can spread to other parts of the body. This study focuses on the breast cancer and its diagnosis with the support of technology. Additionally, also explored the availability of various breast cancer datasets to obtain useful insights, and addressed the Wisconsin Diagnostic Breast Cancer (WDBC) dataset as an appropriate one. As, the WDBC dataset comprises real world clinical data with detailed features of breast mass obtained from biopsies using digitized fine needle aspirate, which make it vital and consistent for differentiating between benign (non-cancerous) and malignant (cancerous) tumors. Moreover, to gather more information from the dataset, utilized various Machine Learning (ML) models based on their suitability for the data. Hence, the main objective of the research project is to apply a diverse range of ML classifiers to evaluate their effectiveness in distinguishing between benign and malignant tumors. This approach follows a defined workflow that includes attribute analysis, data preprocessing, model training and testing, result visualization, and performance optimization. Among the models tested, the CatBoost algorithm demonstrated the highest performance in classifying tumors as benign or malignant.