BREAST CANCER CLASSIFICATION: A COMPARISON OF MACHINE LEARNING MODELS

Abstract

Breast cancer remains one of the most common cancers affecting women globally, and early detection is vital for effective treatment and improved survival rates. This paper presents a comparative analysis of three supervised machine learning algorithms—Logistic Regression, Support Vector Machine (SVM), and Random Forest—for classifying breast tumors as benign or malignant. The experiments were conducted on the Breast Cancer Wisconsin Diagnostic Dataset, containing 30 numerical features derived from medical imaging. Each model was trained and tested using an 80:20 train- test split. Among the models evaluated, the Support Vector Machine (SVM) achieved the highest test accuracy of 94.7%, outperforming both Logistic Regression and Random Forest in terms of generalization performance. A user- friendly interface was also developed using Gradio to facilitate real-time predictions. The results confirm that SVM is a highly effective algorithm for breast cancer classification and demonstrates strong potential for deployment in clinical decision-support systems.