Breast cancer is regarded as the primary cause of death in women. Therefore, timely diagnosis is essential for the patient to recover from it. In this study, a novel supervised machine-learning based-approach is developed to detect breast cancer. A feature-selection algorithm is used to extract the optimal feature from the Wisconsin Breast Cancer (WBC) dataset and then some well-known cutting-edge supervised machine learning models are used to detect cancerous cell nuclei. Finally, a voting ensemble algorithm is used to enhance the detection accuracy of the proposed approach. The approach delivers 98.07% accuracy, 98.09% precision, 96.7% recall and 97.39% F1 in differentiating malignant and benign tumours in the WBC dataset.